Upload folder using huggingface_hub

README.md

@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the train dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2338
-- Accuracy: 0.9602
+- Loss: 0.2260
+- Accuracy: 0.9587
 
 ## Model description
 
@@ -45,34 +45,34 @@ The following hyperparameters were used during training:
 - eval_batch_size: 2
 - seed: 42
 - distributed_type: multi-GPU
-- num_devices: 3
+- num_devices: 4
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 24
-- total_eval_batch_size: 6
-- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- total_train_batch_size: 32
+- total_eval_batch_size: 8
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.03
 - num_epochs: 9.0
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
-|:-------------:|:------:|:----:|:---------------:|:--------:|
-| 0.3408        | 1.0    | 42   | 0.2954          | 0.9288   |
-| 0.1923        | 2.0    | 84   | 0.2233          | 0.9454   |
-| 0.1369        | 3.0    | 126  | 0.1945          | 0.9522   |
-| 0.1333        | 4.0    | 168  | 0.1867          | 0.9564   |
-| 0.0738        | 5.0    | 210  | 0.1909          | 0.9573   |
-| 0.0549        | 6.0    | 252  | 0.2025          | 0.9595   |
-| 0.0246        | 7.0    | 294  | 0.2197          | 0.9601   |
-| 0.0216        | 8.0    | 336  | 0.2324          | 0.9601   |
-| 0.0131        | 8.7904 | 369  | 0.2338          | 0.9602   |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.3179        | 1.0   | 32   | 0.3321          | 0.9217   |
+| 0.206         | 2.0   | 64   | 0.2425          | 0.9408   |
+| 0.1447        | 3.0   | 96   | 0.2109          | 0.9489   |
+| 0.1067        | 4.0   | 128  | 0.2062          | 0.9527   |
+| 0.0612        | 5.0   | 160  | 0.2128          | 0.9539   |
+| 0.0491        | 6.0   | 192  | 0.2169          | 0.9549   |
+| 0.0378        | 7.0   | 224  | 0.2166          | 0.9584   |
+| 0.0294        | 8.0   | 256  | 0.2224          | 0.9588   |
+| 0.0215        | 9.0   | 288  | 0.2260          | 0.9587   |
 
 
 ### Framework versions
 
 - PEFT 0.15.2
-- Transformers 4.51.3
-- Pytorch 2.7.1+cu126
+- Transformers 4.52.4
+- Pytorch 2.7.0
 - Datasets 3.6.0
 - Tokenizers 0.21.1

adapter_config.json

@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "down_proj",
+    "k_proj",
+    "q_proj",
+    "up_proj",
     "v_proj",
-    "gate_proj",
     "o_proj",
-    "k_proj",
-    "up_proj"
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:258e40ef65409d838f1d7c3aa128c7e065fb5d7c444f81cab3006e7bfb0f988d
+oid sha256:395c8edd8df9471f125ca70e8a35dfb39c0abfe28d9cd9e40c40ffae0462f6b3
 size 335604696

all_results.json

@@ -1,13 +1,15 @@
 {
-    "epoch": 8.790419161676647,
-    "eval_accuracy": 0.9601709260426984,
-    "eval_loss": 0.23376664519309998,
-    "eval_runtime": 29.1377,
-    "eval_samples_per_second": 13.213,
-    "eval_steps_per_second": 2.231,
-    "total_flos": 3.347106394674299e+17,
-    "train_loss": 0.14184355957882838,
-    "train_runtime": 2687.5102,
-    "train_samples_per_second": 3.349,
-    "train_steps_per_second": 0.137
+    "effective_tokens_per_sec": 883.9641081528283,
+    "epoch": 9.0,
+    "eval_accuracy": 0.7600996823134496,
+    "eval_loss": 1.411633849143982,
+    "eval_model_preparation_time": 0.0052,
+    "eval_runtime": 17.4477,
+    "eval_samples_per_second": 22.066,
+    "eval_steps_per_second": 2.808,
+    "total_flos": 3.408776235570954e+17,
+    "train_loss": 0.1565158217627969,
+    "train_runtime": 2068.3583,
+    "train_samples_per_second": 4.351,
+    "train_steps_per_second": 0.139
 }

chat_template.jinja

@@ -0,0 +1,87 @@
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
+
+{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
+{%- set ns = namespace() %}
+{%- set ns.index = 0 %}
+{%- for message in loop_messages %}
+    {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
+        {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
+            {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
+        {%- endif %}
+        {%- set ns.index = ns.index + 1 %}
+    {%- endif %}
+{%- endfor %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if message["role"] == "user" %}
+        {%- if tools is not none and (message == user_messages[-1]) %}
+            {{- "[AVAILABLE_TOOLS] [" }}
+            {%- for tool in tools %}
+                {%- set tool = tool.function %}
+                {{- '{"type": "function", "function": {' }}
+                {%- for key, val in tool.items() if key != "return" %}
+                    {%- if val is string %}
+                        {{- '"' + key + '": "' + val + '"' }}
+                    {%- else %}
+                        {{- '"' + key + '": ' + val|tojson }}
+                    {%- endif %}
+                    {%- if not loop.last %}
+                        {{- ", " }}
+                    {%- endif %}
+                {%- endfor %}
+                {{- "}}" }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- else %}
+                    {{- "]" }}
+                {%- endif %}
+            {%- endfor %}
+            {{- "[/AVAILABLE_TOOLS]" }}
+            {%- endif %}
+        {%- if loop.last and system_message is defined %}
+            {{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
+        {%- else %}
+            {{- "[INST] " + message["content"] + "[/INST]" }}
+        {%- endif %}
+    {%- elif message.tool_calls is defined and message.tool_calls is not none %}
+        {{- "[TOOL_CALLS] [" }}
+        {%- for tool_call in message.tool_calls %}
+            {%- set out = tool_call.function|tojson %}
+            {{- out[:-1] }}
+            {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
+                {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+            {%- endif %}
+            {{- ', "id": "' + tool_call.id + '"}' }}
+            {%- if not loop.last %}
+                {{- ", " }}
+            {%- else %}
+                {{- "]" + eos_token }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif message["role"] == "assistant" %}
+        {{- " " + message["content"]|trim + eos_token}}
+    {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
+        {%- if message.content is defined and message.content.content is defined %}
+            {%- set content = message.content.content %}
+        {%- else %}
+            {%- set content = message.content %}
+        {%- endif %}
+        {{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
+        {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
+            {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+        {%- endif %}
+        {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
+    {%- else %}
+        {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
+    {%- endif %}
+{%- endfor %}

checkpoint-288/README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

checkpoint-288/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-288/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:395c8edd8df9471f125ca70e8a35dfb39c0abfe28d9cd9e40c40ffae0462f6b3
+size 335604696

checkpoint-288/chat_template.jinja

@@ -0,0 +1,87 @@
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
+
+{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
+{%- set ns = namespace() %}
+{%- set ns.index = 0 %}
+{%- for message in loop_messages %}
+    {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
+        {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
+            {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
+        {%- endif %}
+        {%- set ns.index = ns.index + 1 %}
+    {%- endif %}
+{%- endfor %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if message["role"] == "user" %}
+        {%- if tools is not none and (message == user_messages[-1]) %}
+            {{- "[AVAILABLE_TOOLS] [" }}
+            {%- for tool in tools %}
+                {%- set tool = tool.function %}
+                {{- '{"type": "function", "function": {' }}
+                {%- for key, val in tool.items() if key != "return" %}
+                    {%- if val is string %}
+                        {{- '"' + key + '": "' + val + '"' }}
+                    {%- else %}
+                        {{- '"' + key + '": ' + val|tojson }}
+                    {%- endif %}
+                    {%- if not loop.last %}
+                        {{- ", " }}
+                    {%- endif %}
+                {%- endfor %}
+                {{- "}}" }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- else %}
+                    {{- "]" }}
+                {%- endif %}
+            {%- endfor %}
+            {{- "[/AVAILABLE_TOOLS]" }}
+            {%- endif %}
+        {%- if loop.last and system_message is defined %}
+            {{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
+        {%- else %}
+            {{- "[INST] " + message["content"] + "[/INST]" }}
+        {%- endif %}
+    {%- elif message.tool_calls is defined and message.tool_calls is not none %}
+        {{- "[TOOL_CALLS] [" }}
+        {%- for tool_call in message.tool_calls %}
+            {%- set out = tool_call.function|tojson %}
+            {{- out[:-1] }}
+            {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
+                {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+            {%- endif %}
+            {{- ', "id": "' + tool_call.id + '"}' }}
+            {%- if not loop.last %}
+                {{- ", " }}
+            {%- else %}
+                {{- "]" + eos_token }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif message["role"] == "assistant" %}
+        {{- " " + message["content"]|trim + eos_token}}
+    {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
+        {%- if message.content is defined and message.content.content is defined %}
+            {%- set content = message.content.content %}
+        {%- else %}
+            {%- set content = message.content %}
+        {%- endif %}
+        {{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
+        {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
+            {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+        {%- endif %}
+        {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
+    {%- else %}
+        {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
+    {%- endif %}
+{%- endfor %}

checkpoint-288/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0749d4f3b1f8a5aff43180422c7c968722fc748d85a646b8b00383e8b6e670ef
+size 671467171

checkpoint-288/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bad78c42be969d37fcfa593427e0d62ebe5956cd81ee9938449ef55f7466c58
+size 15429

checkpoint-288/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c78ba88966e1fb3724ab1efb789c044f378689aa89fdd2d36b6735e7c888c89
+size 15429

checkpoint-288/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9724db26d57a50a36799bfa006e894baa012a624653ae63d77dd200d196d4fc0
+size 15429

checkpoint-288/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c063dbf222a7b1c49c3e2b6d1abd8d1be6be0c6fbf2fda0d4dd0753e21053934
+size 15429

checkpoint-288/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40cb035c4fb1d54485a38b69adcd6e64c8cbd4a55a4cdd3b501c7bc5ef367b63
+size 1465

checkpoint-288/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-288/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

checkpoint-288/trainer_state.json

@@ -0,0 +1,302 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 288,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.9092470407485962,
+      "learning_rate": 0.0001,
+      "loss": 1.0176,
+      "step": 10
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.5211939811706543,
+      "learning_rate": 9.968335515358916e-05,
+      "loss": 0.5103,
+      "step": 20
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.5675566792488098,
+      "learning_rate": 9.873743117270691e-05,
+      "loss": 0.3179,
+      "step": 30
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9217229190183123,
+      "eval_loss": 0.3320535123348236,
+      "eval_runtime": 22.1298,
+      "eval_samples_per_second": 17.397,
+      "eval_steps_per_second": 2.214,
+      "step": 32
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.3762319087982178,
+      "learning_rate": 9.717420893549902e-05,
+      "loss": 0.3371,
+      "step": 40
+    },
+    {
+      "epoch": 1.576,
+      "grad_norm": 0.3366687595844269,
+      "learning_rate": 9.501348789257373e-05,
+      "loss": 0.2708,
+      "step": 50
+    },
+    {
+      "epoch": 1.896,
+      "grad_norm": 0.3178953528404236,
+      "learning_rate": 9.2282635291242e-05,
+      "loss": 0.206,
+      "step": 60
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9407841523692979,
+      "eval_loss": 0.24253705143928528,
+      "eval_runtime": 22.201,
+      "eval_samples_per_second": 17.342,
+      "eval_steps_per_second": 2.207,
+      "step": 64
+    },
+    {
+      "epoch": 2.192,
+      "grad_norm": 0.40763169527053833,
+      "learning_rate": 8.90162395476046e-05,
+      "loss": 0.2057,
+      "step": 70
+    },
+    {
+      "epoch": 2.512,
+      "grad_norm": 0.5000198483467102,
+      "learning_rate": 8.525567215680398e-05,
+      "loss": 0.2043,
+      "step": 80
+    },
+    {
+      "epoch": 2.832,
+      "grad_norm": 0.4025309681892395,
+      "learning_rate": 8.104856369019524e-05,
+      "loss": 0.1447,
+      "step": 90
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9488746080774451,
+      "eval_loss": 0.21092161536216736,
+      "eval_runtime": 22.1138,
+      "eval_samples_per_second": 17.41,
+      "eval_steps_per_second": 2.216,
+      "step": 96
+    },
+    {
+      "epoch": 3.128,
+      "grad_norm": 0.45369309186935425,
+      "learning_rate": 7.644820051634812e-05,
+      "loss": 0.1352,
+      "step": 100
+    },
+    {
+      "epoch": 3.448,
+      "grad_norm": 0.48971518874168396,
+      "learning_rate": 7.15128498868873e-05,
+      "loss": 0.1437,
+      "step": 110
+    },
+    {
+      "epoch": 3.768,
+      "grad_norm": 0.44901880621910095,
+      "learning_rate": 6.630502193549474e-05,
+      "loss": 0.1067,
+      "step": 120
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9527208148072254,
+      "eval_loss": 0.20618033409118652,
+      "eval_runtime": 22.1302,
+      "eval_samples_per_second": 17.397,
+      "eval_steps_per_second": 2.214,
+      "step": 128
+    },
+    {
+      "epoch": 4.064,
+      "grad_norm": 0.5145038962364197,
+      "learning_rate": 6.0890677937442574e-05,
+      "loss": 0.0916,
+      "step": 130
+    },
+    {
+      "epoch": 4.384,
+      "grad_norm": 0.47537460923194885,
+      "learning_rate": 5.5338394857677945e-05,
+      "loss": 0.1133,
+      "step": 140
+    },
+    {
+      "epoch": 4.704,
+      "grad_norm": 0.5391659736633301,
+      "learning_rate": 4.971849676912172e-05,
+      "loss": 0.0792,
+      "step": 150
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.45107302069664,
+      "learning_rate": 4.410216414245771e-05,
+      "loss": 0.0612,
+      "step": 160
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9539307285858623,
+      "eval_loss": 0.2128402590751648,
+      "eval_runtime": 22.0764,
+      "eval_samples_per_second": 17.439,
+      "eval_steps_per_second": 2.22,
+      "step": 160
+    },
+    {
+      "epoch": 5.32,
+      "grad_norm": 0.42281967401504517,
+      "learning_rate": 3.856053228896442e-05,
+      "loss": 0.091,
+      "step": 170
+    },
+    {
+      "epoch": 5.64,
+      "grad_norm": 0.4220280945301056,
+      "learning_rate": 3.316379037532644e-05,
+      "loss": 0.0605,
+      "step": 180
+    },
+    {
+      "epoch": 5.96,
+      "grad_norm": 0.42120489478111267,
+      "learning_rate": 2.798029242211828e-05,
+      "loss": 0.0491,
+      "step": 190
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9549008431419458,
+      "eval_loss": 0.2168993204832077,
+      "eval_runtime": 22.0945,
+      "eval_samples_per_second": 17.425,
+      "eval_steps_per_second": 2.218,
+      "step": 192
+    },
+    {
+      "epoch": 6.256,
+      "grad_norm": 0.5049369931221008,
+      "learning_rate": 2.3075691545870558e-05,
+      "loss": 0.0648,
+      "step": 200
+    },
+    {
+      "epoch": 6.576,
+      "grad_norm": 0.30912792682647705,
+      "learning_rate": 1.8512108410229878e-05,
+      "loss": 0.0431,
+      "step": 210
+    },
+    {
+      "epoch": 6.896,
+      "grad_norm": 0.3820810616016388,
+      "learning_rate": 1.434734441843899e-05,
+      "loss": 0.0378,
+      "step": 220
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9584459654324948,
+      "eval_loss": 0.2166266143321991,
+      "eval_runtime": 22.0992,
+      "eval_samples_per_second": 17.421,
+      "eval_steps_per_second": 2.217,
+      "step": 224
+    },
+    {
+      "epoch": 7.192,
+      "grad_norm": 0.37598758935928345,
+      "learning_rate": 1.063414961267859e-05,
+      "loss": 0.0383,
+      "step": 230
+    },
+    {
+      "epoch": 7.5120000000000005,
+      "grad_norm": 0.4298418164253235,
+      "learning_rate": 7.41955455290726e-06,
+      "loss": 0.0415,
+      "step": 240
+    },
+    {
+      "epoch": 7.832,
+      "grad_norm": 0.2122349590063095,
+      "learning_rate": 4.744274637483936e-06,
+      "loss": 0.0294,
+      "step": 250
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.958849415172974,
+      "eval_loss": 0.22243177890777588,
+      "eval_runtime": 22.0378,
+      "eval_samples_per_second": 17.47,
+      "eval_steps_per_second": 2.223,
+      "step": 256
+    },
+    {
+      "epoch": 8.128,
+      "grad_norm": 0.3120996654033661,
+      "learning_rate": 2.6421944103256657e-06,
+      "loss": 0.0265,
+      "step": 260
+    },
+    {
+      "epoch": 8.448,
+      "grad_norm": 0.21991710364818573,
+      "learning_rate": 1.1399383862592927e-06,
+      "loss": 0.0371,
+      "step": 270
+    },
+    {
+      "epoch": 8.768,
+      "grad_norm": 0.2127743661403656,
+      "learning_rate": 2.5653383040524227e-07,
+      "loss": 0.0215,
+      "step": 280
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 288,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.408776235570954e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-288/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:354801f367c7967ad9c20c19707170444d023f1315154f1bc295d4b4e5415688
+size 6097

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 8.790419161676647,
-    "eval_accuracy": 0.9601709260426984,
-    "eval_loss": 0.23376664519309998,
-    "eval_runtime": 29.1377,
-    "eval_samples_per_second": 13.213,
-    "eval_steps_per_second": 2.231
+    "eval_accuracy": 0.7600996823134496,
+    "eval_loss": 1.411633849143982,
+    "eval_model_preparation_time": 0.0052,
+    "eval_runtime": 17.4477,
+    "eval_samples_per_second": 22.066,
+    "eval_steps_per_second": 2.808
 }

runs/Aug01_22-19-27_104-171-203-173/events.out.tfevents.1754086873.104-171-203-173.9305.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ec94bcb3bab8431d7247abd8376e33a7be21d406bbadaabfce607f798507fd9
+size 14409

runs/Aug01_22-19-27_104-171-203-173/events.out.tfevents.1754088963.104-171-203-173.9305.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:082cb3fd5a6df80c97aa5e6961f379e3f963e2b029fec31ff2412e1c792d3a51
+size 411

runs/Aug01_22-57-11_104-171-203-173/events.out.tfevents.1754089058.104-171-203-173.11873.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb31d6e06079a66150b96a0bce6f42d102daafffc8d15d2e5e470c641ae8d952
+size 409

tokenizer_config.json

@@ -6173,7 +6173,6 @@
     }
   },
   "bos_token": "<s>",
-  "chat_template": "{%- if messages[0][\"role\"] == \"system\" %}\n    {%- set system_message = messages[0][\"content\"] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n{%- set user_messages = loop_messages | selectattr(\"role\", \"equalto\", \"user\") | list %}\n\n{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}\n{%- set ns = namespace() %}\n{%- set ns.index = 0 %}\n{%- for message in loop_messages %}\n    {%- if not (message.role == \"tool\" or message.role == \"tool_results\" or (message.tool_calls is defined and message.tool_calls is not none)) %}\n        {%- if (message[\"role\"] == \"user\") != (ns.index % 2 == 0) %}\n            {{- raise_exception(\"After the optional system message, conversation roles must alternate user/assistant/user/assistant/...\") }}\n        {%- endif %}\n        {%- set ns.index = ns.index + 1 %}\n    {%- endif %}\n{%- endfor %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n    {%- if message[\"role\"] == \"user\" %}\n        {%- if tools is not none and (message == user_messages[-1]) %}\n            {{- \"[AVAILABLE_TOOLS] [\" }}\n            {%- for tool in tools %}\n                {%- set tool = tool.function %}\n                {{- '{\"type\": \"function\", \"function\": {' }}\n                {%- for key, val in tool.items() if key != \"return\" %}\n                    {%- if val is string %}\n                        {{- '\"' + key + '\": \"' + val + '\"' }}\n                    {%- else %}\n                        {{- '\"' + key + '\": ' + val|tojson }}\n                    {%- endif %}\n                    {%- if not loop.last %}\n                        {{- \", \" }}\n                    {%- endif %}\n                {%- endfor %}\n                {{- \"}}\" }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- else %}\n                    {{- \"]\" }}\n                {%- endif %}\n            {%- endfor %}\n            {{- \"[/AVAILABLE_TOOLS]\" }}\n            {%- endif %}\n        {%- if loop.last and system_message is defined %}\n            {{- \"[INST] \" + system_message + \"\\n\\n\" + message[\"content\"] + \"[/INST]\" }}\n        {%- else %}\n            {{- \"[INST] \" + message[\"content\"] + \"[/INST]\" }}\n        {%- endif %}\n    {%- elif message.tool_calls is defined and message.tool_calls is not none %}\n        {{- \"[TOOL_CALLS] [\" }}\n        {%- for tool_call in message.tool_calls %}\n            {%- set out = tool_call.function|tojson %}\n            {{- out[:-1] }}\n            {%- if not tool_call.id is defined or tool_call.id|length != 9 %}\n                {{- raise_exception(\"Tool call IDs should be alphanumeric strings with length 9!\") }}\n            {%- endif %}\n            {{- ', \"id\": \"' + tool_call.id + '\"}' }}\n            {%- if not loop.last %}\n                {{- \", \" }}\n            {%- else %}\n                {{- \"]\" + eos_token }}\n            {%- endif %}\n        {%- endfor %}\n    {%- elif message[\"role\"] == \"assistant\" %}\n        {{- \" \" + message[\"content\"]|trim + eos_token}}\n    {%- elif message[\"role\"] == \"tool_results\" or message[\"role\"] == \"tool\" %}\n        {%- if message.content is defined and message.content.content is defined %}\n            {%- set content = message.content.content %}\n        {%- else %}\n            {%- set content = message.content %}\n        {%- endif %}\n        {{- '[TOOL_RESULTS] {\"content\": ' + content|string + \", \" }}\n        {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}\n            {{- raise_exception(\"Tool call IDs should be alphanumeric strings with length 9!\") }}\n        {%- endif %}\n        {{- '\"call_id\": \"' + message.tool_call_id + '\"}[/TOOL_RESULTS]' }}\n    {%- else %}\n        {{- raise_exception(\"Only user and assistant roles are supported, with the exception of an initial optional system message!\") }}\n    {%- endif %}\n{%- endfor %}\n",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "extra_special_tokens": {},

train_results.json

@@ -1,8 +1,9 @@
 {
-    "epoch": 8.790419161676647,
-    "total_flos": 3.347106394674299e+17,
-    "train_loss": 0.14184355957882838,
-    "train_runtime": 2687.5102,
-    "train_samples_per_second": 3.349,
-    "train_steps_per_second": 0.137
+    "effective_tokens_per_sec": 883.9641081528283,
+    "epoch": 9.0,
+    "total_flos": 3.408776235570954e+17,
+    "train_loss": 0.1565158217627969,
+    "train_runtime": 2068.3583,
+    "train_samples_per_second": 4.351,
+    "train_steps_per_second": 0.139
 }

trainer_log.jsonl

@@ -1,46 +1,48 @@
-{"current_steps": 10, "total_steps": 369, "loss": 1.0376, "lr": 7.500000000000001e-05, "epoch": 0.23952095808383234, "percentage": 2.71, "elapsed_time": "0:01:04", "remaining_time": "0:38:46"}
-{"current_steps": 20, "total_steps": 369, "loss": 0.5249, "lr": 9.990516643685222e-05, "epoch": 0.47904191616766467, "percentage": 5.42, "elapsed_time": "0:02:09", "remaining_time": "0:37:31"}
-{"current_steps": 30, "total_steps": 369, "loss": 0.3878, "lr": 9.944154131125642e-05, "epoch": 0.718562874251497, "percentage": 8.13, "elapsed_time": "0:03:14", "remaining_time": "0:36:39"}
-{"current_steps": 40, "total_steps": 369, "loss": 0.3408, "lr": 9.859528969650738e-05, "epoch": 0.9580838323353293, "percentage": 10.84, "elapsed_time": "0:04:21", "remaining_time": "0:35:50"}
-{"current_steps": 42, "total_steps": 369, "eval_loss": 0.29543060064315796, "epoch": 1.0, "percentage": 11.38, "elapsed_time": "0:05:02", "remaining_time": "0:39:17"}
-{"current_steps": 50, "total_steps": 369, "loss": 0.2531, "lr": 9.737296070648186e-05, "epoch": 1.1916167664670658, "percentage": 13.55, "elapsed_time": "0:05:57", "remaining_time": "0:38:00"}
-{"current_steps": 60, "total_steps": 369, "loss": 0.2522, "lr": 9.57840139057007e-05, "epoch": 1.4311377245508983, "percentage": 16.26, "elapsed_time": "0:07:03", "remaining_time": "0:36:18"}
-{"current_steps": 70, "total_steps": 369, "loss": 0.2588, "lr": 9.384074610206495e-05, "epoch": 1.6706586826347305, "percentage": 18.97, "elapsed_time": "0:08:08", "remaining_time": "0:34:48"}
-{"current_steps": 80, "total_steps": 369, "loss": 0.1923, "lr": 9.155819618225708e-05, "epoch": 1.910179640718563, "percentage": 21.68, "elapsed_time": "0:09:15", "remaining_time": "0:33:26"}
-{"current_steps": 84, "total_steps": 369, "eval_loss": 0.22325021028518677, "epoch": 2.0, "percentage": 22.76, "elapsed_time": "0:10:08", "remaining_time": "0:34:25"}
-{"current_steps": 90, "total_steps": 369, "loss": 0.2022, "lr": 8.895402872628352e-05, "epoch": 2.143712574850299, "percentage": 24.39, "elapsed_time": "0:10:49", "remaining_time": "0:33:32"}
-{"current_steps": 100, "total_steps": 369, "loss": 0.1489, "lr": 8.604839730186125e-05, "epoch": 2.3832335329341316, "percentage": 27.1, "elapsed_time": "0:11:55", "remaining_time": "0:32:04"}
-{"current_steps": 110, "total_steps": 369, "loss": 0.1807, "lr": 8.286378849660896e-05, "epoch": 2.622754491017964, "percentage": 29.81, "elapsed_time": "0:13:01", "remaining_time": "0:30:39"}
-{"current_steps": 120, "total_steps": 369, "loss": 0.1369, "lr": 7.942484789507283e-05, "epoch": 2.8622754491017965, "percentage": 32.52, "elapsed_time": "0:14:07", "remaining_time": "0:29:17"}
-{"current_steps": 126, "total_steps": 369, "eval_loss": 0.19450804591178894, "epoch": 3.0, "percentage": 34.15, "elapsed_time": "0:15:13", "remaining_time": "0:29:22"}
-{"current_steps": 130, "total_steps": 369, "loss": 0.1228, "lr": 7.57581893473448e-05, "epoch": 3.095808383233533, "percentage": 35.23, "elapsed_time": "0:15:40", "remaining_time": "0:28:48"}
-{"current_steps": 140, "total_steps": 369, "loss": 0.0949, "lr": 7.18921890053375e-05, "epoch": 3.3353293413173652, "percentage": 37.94, "elapsed_time": "0:16:45", "remaining_time": "0:27:25"}
-{"current_steps": 150, "total_steps": 369, "loss": 0.1072, "lr": 6.785676572066225e-05, "epoch": 3.5748502994011977, "percentage": 40.65, "elapsed_time": "0:17:52", "remaining_time": "0:26:05"}
-{"current_steps": 160, "total_steps": 369, "loss": 0.1333, "lr": 6.368314950360415e-05, "epoch": 3.81437125748503, "percentage": 43.36, "elapsed_time": "0:18:57", "remaining_time": "0:24:45"}
-{"current_steps": 168, "total_steps": 369, "eval_loss": 0.18670041859149933, "epoch": 4.0, "percentage": 45.53, "elapsed_time": "0:20:18", "remaining_time": "0:24:17"}
-{"current_steps": 170, "total_steps": 369, "loss": 0.0838, "lr": 5.940363983508257e-05, "epoch": 4.047904191616767, "percentage": 46.07, "elapsed_time": "0:20:31", "remaining_time": "0:24:01"}
-{"current_steps": 180, "total_steps": 369, "loss": 0.0805, "lr": 5.5051355702012893e-05, "epoch": 4.287425149700598, "percentage": 48.78, "elapsed_time": "0:21:38", "remaining_time": "0:22:43"}
-{"current_steps": 190, "total_steps": 369, "loss": 0.0664, "lr": 5.0659979290537954e-05, "epoch": 4.526946107784431, "percentage": 51.49, "elapsed_time": "0:22:43", "remaining_time": "0:21:24"}
-{"current_steps": 200, "total_steps": 369, "loss": 0.0628, "lr": 4.626349532067879e-05, "epoch": 4.766467065868263, "percentage": 54.2, "elapsed_time": "0:23:49", "remaining_time": "0:20:07"}
-{"current_steps": 210, "total_steps": 369, "loss": 0.0738, "lr": 4.189592803968563e-05, "epoch": 5.0, "percentage": 56.91, "elapsed_time": "0:24:52", "remaining_time": "0:18:50"}
-{"current_steps": 210, "total_steps": 369, "eval_loss": 0.19091445207595825, "epoch": 5.0, "percentage": 56.91, "elapsed_time": "0:25:22", "remaining_time": "0:19:12"}
-{"current_steps": 220, "total_steps": 369, "loss": 0.046, "lr": 3.759107790948882e-05, "epoch": 5.2395209580838324, "percentage": 59.62, "elapsed_time": "0:26:28", "remaining_time": "0:17:55"}
-{"current_steps": 230, "total_steps": 369, "loss": 0.0464, "lr": 3.338226002601703e-05, "epoch": 5.479041916167665, "percentage": 62.33, "elapsed_time": "0:27:34", "remaining_time": "0:16:39"}
-{"current_steps": 240, "total_steps": 369, "loss": 0.0438, "lr": 2.9302046294747497e-05, "epoch": 5.718562874251497, "percentage": 65.04, "elapsed_time": "0:28:38", "remaining_time": "0:15:23"}
-{"current_steps": 250, "total_steps": 369, "loss": 0.0549, "lr": 2.5382013357782893e-05, "epoch": 5.95808383233533, "percentage": 67.75, "elapsed_time": "0:29:44", "remaining_time": "0:14:09"}
-{"current_steps": 252, "total_steps": 369, "eval_loss": 0.2025168389081955, "epoch": 6.0, "percentage": 68.29, "elapsed_time": "0:30:25", "remaining_time": "0:14:07"}
-{"current_steps": 260, "total_steps": 369, "loss": 0.038, "lr": 2.1652498223239427e-05, "epoch": 6.191616766467066, "percentage": 70.46, "elapsed_time": "0:31:18", "remaining_time": "0:13:07"}
-{"current_steps": 270, "total_steps": 369, "loss": 0.0453, "lr": 1.814236348812211e-05, "epoch": 6.431137724550898, "percentage": 73.17, "elapsed_time": "0:32:26", "remaining_time": "0:11:53"}
-{"current_steps": 280, "total_steps": 369, "loss": 0.0255, "lr": 1.4878773971620074e-05, "epoch": 6.6706586826347305, "percentage": 75.88, "elapsed_time": "0:33:30", "remaining_time": "0:10:39"}
-{"current_steps": 290, "total_steps": 369, "loss": 0.0246, "lr": 1.1886986487449475e-05, "epoch": 6.910179640718563, "percentage": 78.59, "elapsed_time": "0:34:35", "remaining_time": "0:09:25"}
-{"current_steps": 294, "total_steps": 369, "eval_loss": 0.2196582704782486, "epoch": 7.0, "percentage": 79.67, "elapsed_time": "0:35:29", "remaining_time": "0:09:03"}
-{"current_steps": 300, "total_steps": 369, "loss": 0.0188, "lr": 9.190154382188921e-06, "epoch": 7.1437125748503, "percentage": 81.3, "elapsed_time": "0:36:10", "remaining_time": "0:08:19"}
-{"current_steps": 310, "total_steps": 369, "loss": 0.0199, "lr": 6.809148352279182e-06, "epoch": 7.383233532934132, "percentage": 84.01, "elapsed_time": "0:37:16", "remaining_time": "0:07:05"}
-{"current_steps": 320, "total_steps": 369, "loss": 0.0335, "lr": 4.762394926378477e-06, "epoch": 7.6227544910179645, "percentage": 86.72, "elapsed_time": "0:38:22", "remaining_time": "0:05:52"}
-{"current_steps": 330, "total_steps": 369, "loss": 0.0216, "lr": 3.065733863053072e-06, "epoch": 7.862275449101796, "percentage": 89.43, "elapsed_time": "0:39:28", "remaining_time": "0:04:39"}
-{"current_steps": 336, "total_steps": 369, "eval_loss": 0.232394278049469, "epoch": 8.0, "percentage": 91.06, "elapsed_time": "0:40:36", "remaining_time": "0:03:59"}
-{"current_steps": 340, "total_steps": 369, "loss": 0.0204, "lr": 1.7322955673980678e-06, "epoch": 8.095808383233534, "percentage": 92.14, "elapsed_time": "0:41:02", "remaining_time": "0:03:30"}
-{"current_steps": 350, "total_steps": 369, "loss": 0.0287, "lr": 7.723994752570462e-07, "epoch": 8.335329341317365, "percentage": 94.85, "elapsed_time": "0:42:08", "remaining_time": "0:02:17"}
-{"current_steps": 360, "total_steps": 369, "loss": 0.0131, "lr": 1.9347419144180035e-07, "epoch": 8.574850299401197, "percentage": 97.56, "elapsed_time": "0:43:13", "remaining_time": "0:01:04"}
-{"current_steps": 369, "total_steps": 369, "eval_loss": 0.23376664519309998, "epoch": 8.790419161676647, "percentage": 100.0, "elapsed_time": "0:44:44", "remaining_time": "0:00:00"}
-{"current_steps": 369, "total_steps": 369, "epoch": 8.790419161676647, "percentage": 100.0, "elapsed_time": "0:44:44", "remaining_time": "0:00:00"}
+{"current_steps": 10, "total_steps": 288, "loss": 1.0176, "lr": 0.0001, "epoch": 0.32, "percentage": 3.47, "elapsed_time": "0:01:07", "remaining_time": "0:31:04"}
+{"current_steps": 20, "total_steps": 288, "loss": 0.5103, "lr": 9.968335515358916e-05, "epoch": 0.64, "percentage": 6.94, "elapsed_time": "0:02:12", "remaining_time": "0:29:38"}
+{"current_steps": 30, "total_steps": 288, "loss": 0.3179, "lr": 9.873743117270691e-05, "epoch": 0.96, "percentage": 10.42, "elapsed_time": "0:03:18", "remaining_time": "0:28:24"}
+{"current_steps": 32, "total_steps": 288, "eval_loss": 0.3320535123348236, "epoch": 1.0, "percentage": 11.11, "elapsed_time": "0:03:48", "remaining_time": "0:30:28"}
+{"current_steps": 40, "total_steps": 288, "loss": 0.3371, "lr": 9.717420893549902e-05, "epoch": 1.256, "percentage": 13.89, "elapsed_time": "0:04:43", "remaining_time": "0:29:15"}
+{"current_steps": 50, "total_steps": 288, "loss": 0.2708, "lr": 9.501348789257373e-05, "epoch": 1.576, "percentage": 17.36, "elapsed_time": "0:05:48", "remaining_time": "0:27:38"}
+{"current_steps": 60, "total_steps": 288, "loss": 0.206, "lr": 9.2282635291242e-05, "epoch": 1.896, "percentage": 20.83, "elapsed_time": "0:06:54", "remaining_time": "0:26:15"}
+{"current_steps": 64, "total_steps": 288, "eval_loss": 0.24253705143928528, "epoch": 2.0, "percentage": 22.22, "elapsed_time": "0:07:38", "remaining_time": "0:26:43"}
+{"current_steps": 70, "total_steps": 288, "loss": 0.2057, "lr": 8.90162395476046e-05, "epoch": 2.192, "percentage": 24.31, "elapsed_time": "0:08:19", "remaining_time": "0:25:55"}
+{"current_steps": 80, "total_steps": 288, "loss": 0.2043, "lr": 8.525567215680398e-05, "epoch": 2.512, "percentage": 27.78, "elapsed_time": "0:09:24", "remaining_time": "0:24:28"}
+{"current_steps": 90, "total_steps": 288, "loss": 0.1447, "lr": 8.104856369019524e-05, "epoch": 2.832, "percentage": 31.25, "elapsed_time": "0:10:30", "remaining_time": "0:23:08"}
+{"current_steps": 96, "total_steps": 288, "eval_loss": 0.21092161536216736, "epoch": 3.0, "percentage": 33.33, "elapsed_time": "0:11:27", "remaining_time": "0:22:55"}
+{"current_steps": 100, "total_steps": 288, "loss": 0.1352, "lr": 7.644820051634812e-05, "epoch": 3.128, "percentage": 34.72, "elapsed_time": "0:11:54", "remaining_time": "0:22:23"}
+{"current_steps": 110, "total_steps": 288, "loss": 0.1437, "lr": 7.15128498868873e-05, "epoch": 3.448, "percentage": 38.19, "elapsed_time": "0:13:00", "remaining_time": "0:21:03"}
+{"current_steps": 120, "total_steps": 288, "loss": 0.1067, "lr": 6.630502193549474e-05, "epoch": 3.768, "percentage": 41.67, "elapsed_time": "0:14:07", "remaining_time": "0:19:46"}
+{"current_steps": 128, "total_steps": 288, "eval_loss": 0.20618033409118652, "epoch": 4.0, "percentage": 44.44, "elapsed_time": "0:15:17", "remaining_time": "0:19:06"}
+{"current_steps": 130, "total_steps": 288, "loss": 0.0916, "lr": 6.0890677937442574e-05, "epoch": 4.064, "percentage": 45.14, "elapsed_time": "0:15:31", "remaining_time": "0:18:52"}
+{"current_steps": 140, "total_steps": 288, "loss": 0.1133, "lr": 5.5338394857677945e-05, "epoch": 4.384, "percentage": 48.61, "elapsed_time": "0:16:37", "remaining_time": "0:17:34"}
+{"current_steps": 150, "total_steps": 288, "loss": 0.0792, "lr": 4.971849676912172e-05, "epoch": 4.704, "percentage": 52.08, "elapsed_time": "0:17:43", "remaining_time": "0:16:18"}
+{"current_steps": 160, "total_steps": 288, "loss": 0.0612, "lr": 4.410216414245771e-05, "epoch": 5.0, "percentage": 55.56, "elapsed_time": "0:18:44", "remaining_time": "0:14:59"}
+{"current_steps": 160, "total_steps": 288, "eval_loss": 0.2128402590751648, "epoch": 5.0, "percentage": 55.56, "elapsed_time": "0:19:06", "remaining_time": "0:15:17"}
+{"current_steps": 170, "total_steps": 288, "loss": 0.091, "lr": 3.856053228896442e-05, "epoch": 5.32, "percentage": 59.03, "elapsed_time": "0:20:13", "remaining_time": "0:14:02"}
+{"current_steps": 180, "total_steps": 288, "loss": 0.0605, "lr": 3.316379037532644e-05, "epoch": 5.64, "percentage": 62.5, "elapsed_time": "0:21:19", "remaining_time": "0:12:47"}
+{"current_steps": 190, "total_steps": 288, "loss": 0.0491, "lr": 2.798029242211828e-05, "epoch": 5.96, "percentage": 65.97, "elapsed_time": "0:22:25", "remaining_time": "0:11:34"}
+{"current_steps": 192, "total_steps": 288, "eval_loss": 0.2168993204832077, "epoch": 6.0, "percentage": 66.67, "elapsed_time": "0:22:55", "remaining_time": "0:11:27"}
+{"current_steps": 200, "total_steps": 288, "loss": 0.0648, "lr": 2.3075691545870558e-05, "epoch": 6.256, "percentage": 69.44, "elapsed_time": "0:23:50", "remaining_time": "0:10:29"}
+{"current_steps": 210, "total_steps": 288, "loss": 0.0431, "lr": 1.8512108410229878e-05, "epoch": 6.576, "percentage": 72.92, "elapsed_time": "0:24:55", "remaining_time": "0:09:15"}
+{"current_steps": 220, "total_steps": 288, "loss": 0.0378, "lr": 1.434734441843899e-05, "epoch": 6.896, "percentage": 76.39, "elapsed_time": "0:26:01", "remaining_time": "0:08:02"}
+{"current_steps": 224, "total_steps": 288, "eval_loss": 0.2166266143321991, "epoch": 7.0, "percentage": 77.78, "elapsed_time": "0:26:45", "remaining_time": "0:07:38"}
+{"current_steps": 230, "total_steps": 288, "loss": 0.0383, "lr": 1.063414961267859e-05, "epoch": 7.192, "percentage": 79.86, "elapsed_time": "0:27:26", "remaining_time": "0:06:55"}
+{"current_steps": 240, "total_steps": 288, "loss": 0.0415, "lr": 7.41955455290726e-06, "epoch": 7.5120000000000005, "percentage": 83.33, "elapsed_time": "0:28:31", "remaining_time": "0:05:42"}
+{"current_steps": 250, "total_steps": 288, "loss": 0.0294, "lr": 4.744274637483936e-06, "epoch": 7.832, "percentage": 86.81, "elapsed_time": "0:29:37", "remaining_time": "0:04:30"}
+{"current_steps": 256, "total_steps": 288, "eval_loss": 0.22243177890777588, "epoch": 8.0, "percentage": 88.89, "elapsed_time": "0:30:34", "remaining_time": "0:03:49"}
+{"current_steps": 260, "total_steps": 288, "loss": 0.0265, "lr": 2.6421944103256657e-06, "epoch": 8.128, "percentage": 90.28, "elapsed_time": "0:31:01", "remaining_time": "0:03:20"}
+{"current_steps": 270, "total_steps": 288, "loss": 0.0371, "lr": 1.1399383862592927e-06, "epoch": 8.448, "percentage": 93.75, "elapsed_time": "0:32:07", "remaining_time": "0:02:08"}
+{"current_steps": 280, "total_steps": 288, "loss": 0.0215, "lr": 2.5653383040524227e-07, "epoch": 8.768, "percentage": 97.22, "elapsed_time": "0:33:13", "remaining_time": "0:00:56"}
+{"current_steps": 288, "total_steps": 288, "eval_loss": 0.22601914405822754, "epoch": 9.0, "percentage": 100.0, "elapsed_time": "0:34:25", "remaining_time": "0:00:00"}
+{"current_steps": 288, "total_steps": 288, "epoch": 9.0, "percentage": 100.0, "elapsed_time": "0:34:25", "remaining_time": "0:00:00"}
+{"current_steps": 5, "total_steps": 49, "percentage": 10.2, "elapsed_time": "0:00:01", "remaining_time": "0:00:11"}
+{"current_steps": 10, "total_steps": 49, "percentage": 20.41, "elapsed_time": "0:00:02", "remaining_time": "0:00:11"}
+{"current_steps": 15, "total_steps": 49, "percentage": 30.61, "elapsed_time": "0:00:04", "remaining_time": "0:00:10"}
+{"current_steps": 20, "total_steps": 49, "percentage": 40.82, "elapsed_time": "0:00:06", "remaining_time": "0:00:08"}
+{"current_steps": 25, "total_steps": 49, "percentage": 51.02, "elapsed_time": "0:00:07", "remaining_time": "0:00:07"}
+{"current_steps": 30, "total_steps": 49, "percentage": 61.22, "elapsed_time": "0:00:09", "remaining_time": "0:00:06"}
+{"current_steps": 35, "total_steps": 49, "percentage": 71.43, "elapsed_time": "0:00:11", "remaining_time": "0:00:04"}
+{"current_steps": 40, "total_steps": 49, "percentage": 81.63, "elapsed_time": "0:00:13", "remaining_time": "0:00:02"}
+{"current_steps": 45, "total_steps": 49, "percentage": 91.84, "elapsed_time": "0:00:14", "remaining_time": "0:00:01"}
+{"current_steps": 0, "total_steps": 49, "eval_loss": 1.411633849143982, "percentage": 0.0, "elapsed_time": "0:00:16", "remaining_time": "0:00:00"}

trainer_state.json

@@ -2,358 +2,302 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.790419161676647,
+  "epoch": 9.0,
   "eval_steps": 500,
-  "global_step": 369,
+  "global_step": 288,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.23952095808383234,
-      "grad_norm": 1.0734883546829224,
-      "learning_rate": 7.500000000000001e-05,
-      "loss": 1.0376,
+      "epoch": 0.32,
+      "grad_norm": 0.9092470407485962,
+      "learning_rate": 0.0001,
+      "loss": 1.0176,
       "step": 10
     },
     {
-      "epoch": 0.47904191616766467,
-      "grad_norm": 0.5477334856987,
-      "learning_rate": 9.990516643685222e-05,
-      "loss": 0.5249,
+      "epoch": 0.64,
+      "grad_norm": 0.5211939811706543,
+      "learning_rate": 9.968335515358916e-05,
+      "loss": 0.5103,
       "step": 20
     },
     {
-      "epoch": 0.718562874251497,
-      "grad_norm": 0.5087978839874268,
-      "learning_rate": 9.944154131125642e-05,
-      "loss": 0.3878,
+      "epoch": 0.96,
+      "grad_norm": 0.5675566792488098,
+      "learning_rate": 9.873743117270691e-05,
+      "loss": 0.3179,
       "step": 30
     },
-    {
-      "epoch": 0.9580838323353293,
-      "grad_norm": 0.4627484977245331,
-      "learning_rate": 9.859528969650738e-05,
-      "loss": 0.3408,
-      "step": 40
-    },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.9287885233004581,
-      "eval_loss": 0.29543060064315796,
-      "eval_runtime": 29.2437,
-      "eval_samples_per_second": 13.165,
-      "eval_steps_per_second": 2.223,
-      "step": 42
+      "eval_accuracy": 0.9217229190183123,
+      "eval_loss": 0.3320535123348236,
+      "eval_runtime": 22.1298,
+      "eval_samples_per_second": 17.397,
+      "eval_steps_per_second": 2.214,
+      "step": 32
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.3762319087982178,
+      "learning_rate": 9.717420893549902e-05,
+      "loss": 0.3371,
+      "step": 40
     },
     {
-      "epoch": 1.1916167664670658,
-      "grad_norm": 0.4231412708759308,
-      "learning_rate": 9.737296070648186e-05,
-      "loss": 0.2531,
+      "epoch": 1.576,
+      "grad_norm": 0.3366687595844269,
+      "learning_rate": 9.501348789257373e-05,
+      "loss": 0.2708,
       "step": 50
     },
     {
-      "epoch": 1.4311377245508983,
-      "grad_norm": 0.5066399574279785,
-      "learning_rate": 9.57840139057007e-05,
-      "loss": 0.2522,
+      "epoch": 1.896,
+      "grad_norm": 0.3178953528404236,
+      "learning_rate": 9.2282635291242e-05,
+      "loss": 0.206,
       "step": 60
     },
     {
-      "epoch": 1.6706586826347305,
-      "grad_norm": 0.5796340703964233,
-      "learning_rate": 9.384074610206495e-05,
-      "loss": 0.2588,
+      "epoch": 2.0,
+      "eval_accuracy": 0.9407841523692979,
+      "eval_loss": 0.24253705143928528,
+      "eval_runtime": 22.201,
+      "eval_samples_per_second": 17.342,
+      "eval_steps_per_second": 2.207,
+      "step": 64
+    },
+    {
+      "epoch": 2.192,
+      "grad_norm": 0.40763169527053833,
+      "learning_rate": 8.90162395476046e-05,
+      "loss": 0.2057,
       "step": 70
     },
     {
-      "epoch": 1.910179640718563,
-      "grad_norm": 0.431496262550354,
-      "learning_rate": 9.155819618225708e-05,
-      "loss": 0.1923,
+      "epoch": 2.512,
+      "grad_norm": 0.5000198483467102,
+      "learning_rate": 8.525567215680398e-05,
+      "loss": 0.2043,
       "step": 80
     },
     {
-      "epoch": 2.0,
-      "eval_accuracy": 0.9453862057863471,
-      "eval_loss": 0.22325021028518677,
-      "eval_runtime": 29.1713,
-      "eval_samples_per_second": 13.198,
-      "eval_steps_per_second": 2.228,
-      "step": 84
-    },
-    {
-      "epoch": 2.143712574850299,
-      "grad_norm": 0.3872606158256531,
-      "learning_rate": 8.895402872628352e-05,
-      "loss": 0.2022,
+      "epoch": 2.832,
+      "grad_norm": 0.4025309681892395,
+      "learning_rate": 8.104856369019524e-05,
+      "loss": 0.1447,
       "step": 90
     },
     {
-      "epoch": 2.3832335329341316,
-      "grad_norm": 0.5072871446609497,
-      "learning_rate": 8.604839730186125e-05,
-      "loss": 0.1489,
+      "epoch": 3.0,
+      "eval_accuracy": 0.9488746080774451,
+      "eval_loss": 0.21092161536216736,
+      "eval_runtime": 22.1138,
+      "eval_samples_per_second": 17.41,
+      "eval_steps_per_second": 2.216,
+      "step": 96
+    },
+    {
+      "epoch": 3.128,
+      "grad_norm": 0.45369309186935425,
+      "learning_rate": 7.644820051634812e-05,
+      "loss": 0.1352,
       "step": 100
     },
     {
-      "epoch": 2.622754491017964,
-      "grad_norm": 0.5924299955368042,
-      "learning_rate": 8.286378849660896e-05,
-      "loss": 0.1807,
+      "epoch": 3.448,
+      "grad_norm": 0.48971518874168396,
+      "learning_rate": 7.15128498868873e-05,
+      "loss": 0.1437,
       "step": 110
     },
     {
-      "epoch": 2.8622754491017965,
-      "grad_norm": 0.5023337602615356,
-      "learning_rate": 7.942484789507283e-05,
-      "loss": 0.1369,
+      "epoch": 3.768,
+      "grad_norm": 0.44901880621910095,
+      "learning_rate": 6.630502193549474e-05,
+      "loss": 0.1067,
       "step": 120
     },
     {
-      "epoch": 3.0,
-      "eval_accuracy": 0.9521505982560647,
-      "eval_loss": 0.19450804591178894,
-      "eval_runtime": 29.0414,
-      "eval_samples_per_second": 13.257,
-      "eval_steps_per_second": 2.238,
-      "step": 126
-    },
-    {
-      "epoch": 3.095808383233533,
-      "grad_norm": 0.4512905180454254,
-      "learning_rate": 7.57581893473448e-05,
-      "loss": 0.1228,
+      "epoch": 4.0,
+      "eval_accuracy": 0.9527208148072254,
+      "eval_loss": 0.20618033409118652,
+      "eval_runtime": 22.1302,
+      "eval_samples_per_second": 17.397,
+      "eval_steps_per_second": 2.214,
+      "step": 128
+    },
+    {
+      "epoch": 4.064,
+      "grad_norm": 0.5145038962364197,
+      "learning_rate": 6.0890677937442574e-05,
+      "loss": 0.0916,
       "step": 130
     },
     {
-      "epoch": 3.3353293413173652,
-      "grad_norm": 0.43206489086151123,
-      "learning_rate": 7.18921890053375e-05,
-      "loss": 0.0949,
+      "epoch": 4.384,
+      "grad_norm": 0.47537460923194885,
+      "learning_rate": 5.5338394857677945e-05,
+      "loss": 0.1133,
       "step": 140
     },
     {
-      "epoch": 3.5748502994011977,
-      "grad_norm": 0.43717867136001587,
-      "learning_rate": 6.785676572066225e-05,
-      "loss": 0.1072,
+      "epoch": 4.704,
+      "grad_norm": 0.5391659736633301,
+      "learning_rate": 4.971849676912172e-05,
+      "loss": 0.0792,
       "step": 150
     },
     {
-      "epoch": 3.81437125748503,
-      "grad_norm": 0.5549845695495605,
-      "learning_rate": 6.368314950360415e-05,
-      "loss": 0.1333,
+      "epoch": 5.0,
+      "grad_norm": 0.45107302069664,
+      "learning_rate": 4.410216414245771e-05,
+      "loss": 0.0612,
       "step": 160
     },
     {
-      "epoch": 4.0,
-      "eval_accuracy": 0.9563760579587307,
-      "eval_loss": 0.18670041859149933,
-      "eval_runtime": 29.043,
-      "eval_samples_per_second": 13.256,
-      "eval_steps_per_second": 2.238,
-      "step": 168
-    },
-    {
-      "epoch": 4.047904191616767,
-      "grad_norm": 0.3298746645450592,
-      "learning_rate": 5.940363983508257e-05,
-      "loss": 0.0838,
+      "epoch": 5.0,
+      "eval_accuracy": 0.9539307285858623,
+      "eval_loss": 0.2128402590751648,
+      "eval_runtime": 22.0764,
+      "eval_samples_per_second": 17.439,
+      "eval_steps_per_second": 2.22,
+      "step": 160
+    },
+    {
+      "epoch": 5.32,
+      "grad_norm": 0.42281967401504517,
+      "learning_rate": 3.856053228896442e-05,
+      "loss": 0.091,
       "step": 170
     },
     {
-      "epoch": 4.287425149700598,
-      "grad_norm": 0.5451555252075195,
-      "learning_rate": 5.5051355702012893e-05,
-      "loss": 0.0805,
+      "epoch": 5.64,
+      "grad_norm": 0.4220280945301056,
+      "learning_rate": 3.316379037532644e-05,
+      "loss": 0.0605,
       "step": 180
     },
     {
-      "epoch": 4.526946107784431,
-      "grad_norm": 0.5960578322410583,
-      "learning_rate": 5.0659979290537954e-05,
-      "loss": 0.0664,
+      "epoch": 5.96,
+      "grad_norm": 0.42120489478111267,
+      "learning_rate": 2.798029242211828e-05,
+      "loss": 0.0491,
       "step": 190
     },
     {
-      "epoch": 4.766467065868263,
-      "grad_norm": 0.5429267883300781,
-      "learning_rate": 4.626349532067879e-05,
-      "loss": 0.0628,
+      "epoch": 6.0,
+      "eval_accuracy": 0.9549008431419458,
+      "eval_loss": 0.2168993204832077,
+      "eval_runtime": 22.0945,
+      "eval_samples_per_second": 17.425,
+      "eval_steps_per_second": 2.218,
+      "step": 192
+    },
+    {
+      "epoch": 6.256,
+      "grad_norm": 0.5049369931221008,
+      "learning_rate": 2.3075691545870558e-05,
+      "loss": 0.0648,
       "step": 200
     },
     {
-      "epoch": 5.0,
-      "grad_norm": 0.43659478425979614,
-      "learning_rate": 4.189592803968563e-05,
-      "loss": 0.0738,
-      "step": 210
-    },
-    {
-      "epoch": 5.0,
-      "eval_accuracy": 0.9573371652464306,
-      "eval_loss": 0.19091445207595825,
-      "eval_runtime": 29.1306,
-      "eval_samples_per_second": 13.216,
-      "eval_steps_per_second": 2.231,
+      "epoch": 6.576,
+      "grad_norm": 0.30912792682647705,
+      "learning_rate": 1.8512108410229878e-05,
+      "loss": 0.0431,
       "step": 210
     },
     {
-      "epoch": 5.2395209580838324,
-      "grad_norm": 0.36590853333473206,
-      "learning_rate": 3.759107790948882e-05,
-      "loss": 0.046,
+      "epoch": 6.896,
+      "grad_norm": 0.3820810616016388,
+      "learning_rate": 1.434734441843899e-05,
+      "loss": 0.0378,
       "step": 220
     },
     {
-      "epoch": 5.479041916167665,
-      "grad_norm": 0.4938795566558838,
-      "learning_rate": 3.338226002601703e-05,
-      "loss": 0.0464,
+      "epoch": 7.0,
+      "eval_accuracy": 0.9584459654324948,
+      "eval_loss": 0.2166266143321991,
+      "eval_runtime": 22.0992,
+      "eval_samples_per_second": 17.421,
+      "eval_steps_per_second": 2.217,
+      "step": 224
+    },
+    {
+      "epoch": 7.192,
+      "grad_norm": 0.37598758935928345,
+      "learning_rate": 1.063414961267859e-05,
+      "loss": 0.0383,
       "step": 230
     },
     {
-      "epoch": 5.718562874251497,
-      "grad_norm": 0.41811272501945496,
-      "learning_rate": 2.9302046294747497e-05,
-      "loss": 0.0438,
+      "epoch": 7.5120000000000005,
+      "grad_norm": 0.4298418164253235,
+      "learning_rate": 7.41955455290726e-06,
+      "loss": 0.0415,
       "step": 240
     },
     {
-      "epoch": 5.95808383233533,
-      "grad_norm": 0.37814924120903015,
-      "learning_rate": 2.5382013357782893e-05,
-      "loss": 0.0549,
+      "epoch": 7.832,
+      "grad_norm": 0.2122349590063095,
+      "learning_rate": 4.744274637483936e-06,
+      "loss": 0.0294,
       "step": 250
     },
     {
-      "epoch": 6.0,
-      "eval_accuracy": 0.9595451069080204,
-      "eval_loss": 0.2025168389081955,
-      "eval_runtime": 29.0421,
-      "eval_samples_per_second": 13.257,
-      "eval_steps_per_second": 2.238,
-      "step": 252
-    },
-    {
-      "epoch": 6.191616766467066,
-      "grad_norm": 0.4280014634132385,
-      "learning_rate": 2.1652498223239427e-05,
-      "loss": 0.038,
+      "epoch": 8.0,
+      "eval_accuracy": 0.958849415172974,
+      "eval_loss": 0.22243177890777588,
+      "eval_runtime": 22.0378,
+      "eval_samples_per_second": 17.47,
+      "eval_steps_per_second": 2.223,
+      "step": 256
+    },
+    {
+      "epoch": 8.128,
+      "grad_norm": 0.3120996654033661,
+      "learning_rate": 2.6421944103256657e-06,
+      "loss": 0.0265,
       "step": 260
     },
     {
-      "epoch": 6.431137724550898,
-      "grad_norm": 0.367276132106781,
-      "learning_rate": 1.814236348812211e-05,
-      "loss": 0.0453,
+      "epoch": 8.448,
+      "grad_norm": 0.21991710364818573,
+      "learning_rate": 1.1399383862592927e-06,
+      "loss": 0.0371,
       "step": 270
     },
     {
-      "epoch": 6.6706586826347305,
-      "grad_norm": 0.6734885573387146,
-      "learning_rate": 1.4878773971620074e-05,
-      "loss": 0.0255,
+      "epoch": 8.768,
+      "grad_norm": 0.2127743661403656,
+      "learning_rate": 2.5653383040524227e-07,
+      "loss": 0.0215,
       "step": 280
     },
     {
-      "epoch": 6.910179640718563,
-      "grad_norm": 0.43918535113334656,
-      "learning_rate": 1.1886986487449475e-05,
-      "loss": 0.0246,
-      "step": 290
-    },
-    {
-      "epoch": 7.0,
-      "eval_accuracy": 0.9601195563525197,
-      "eval_loss": 0.2196582704782486,
-      "eval_runtime": 29.0921,
-      "eval_samples_per_second": 13.234,
-      "eval_steps_per_second": 2.234,
-      "step": 294
-    },
-    {
-      "epoch": 7.1437125748503,
-      "grad_norm": 0.2443029135465622,
-      "learning_rate": 9.190154382188921e-06,
-      "loss": 0.0188,
-      "step": 300
-    },
-    {
-      "epoch": 7.383233532934132,
-      "grad_norm": 0.2125871330499649,
-      "learning_rate": 6.809148352279182e-06,
-      "loss": 0.0199,
-      "step": 310
+      "epoch": 9.0,
+      "eval_accuracy": 0.9587168946755322,
+      "eval_loss": 0.22601914405822754,
+      "eval_runtime": 22.0034,
+      "eval_samples_per_second": 17.497,
+      "eval_steps_per_second": 2.227,
+      "step": 288
     },
     {
-      "epoch": 7.6227544910179645,
-      "grad_norm": 0.25036877393722534,
-      "learning_rate": 4.762394926378477e-06,
-      "loss": 0.0335,
-      "step": 320
-    },
-    {
-      "epoch": 7.862275449101796,
-      "grad_norm": 0.2146039605140686,
-      "learning_rate": 3.065733863053072e-06,
-      "loss": 0.0216,
-      "step": 330
-    },
-    {
-      "epoch": 8.0,
-      "eval_accuracy": 0.9601274555153836,
-      "eval_loss": 0.232394278049469,
-      "eval_runtime": 29.1106,
-      "eval_samples_per_second": 13.225,
-      "eval_steps_per_second": 2.233,
-      "step": 336
-    },
-    {
-      "epoch": 8.095808383233534,
-      "grad_norm": 0.20316274464130402,
-      "learning_rate": 1.7322955673980678e-06,
-      "loss": 0.0204,
-      "step": 340
-    },
-    {
-      "epoch": 8.335329341317365,
-      "grad_norm": 0.19030429422855377,
-      "learning_rate": 7.723994752570462e-07,
-      "loss": 0.0287,
-      "step": 350
-    },
-    {
-      "epoch": 8.574850299401197,
-      "grad_norm": 0.2464722841978073,
-      "learning_rate": 1.9347419144180035e-07,
-      "loss": 0.0131,
-      "step": 360
-    },
-    {
-      "epoch": 8.790419161676647,
-      "eval_accuracy": 0.9601709260426984,
-      "eval_loss": 0.23376664519309998,
-      "eval_runtime": 29.0302,
-      "eval_samples_per_second": 13.262,
-      "eval_steps_per_second": 2.239,
-      "step": 369
-    },
-    {
-      "epoch": 8.790419161676647,
-      "step": 369,
-      "total_flos": 3.347106394674299e+17,
-      "train_loss": 0.14184355957882838,
-      "train_runtime": 2687.5102,
-      "train_samples_per_second": 3.349,
-      "train_steps_per_second": 0.137
+      "epoch": 9.0,
+      "step": 288,
+      "total_flos": 3.408776235570954e+17,
+      "train_loss": 0.1565158217627969,
+      "train_runtime": 2068.3583,
+      "train_samples_per_second": 4.351,
+      "train_steps_per_second": 0.139
     }
   ],
   "logging_steps": 10,
-  "max_steps": 369,
+  "max_steps": 288,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 9,
   "save_steps": 500,
@@ -369,7 +313,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.347106394674299e+17,
+  "total_flos": 3.408776235570954e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6625c94ac81d774713d80906f0c3c17652ae34d6cb07d755ad005e3fe18320f
+oid sha256:354801f367c7967ad9c20c19707170444d023f1315154f1bc295d4b4e5415688
 size 6097