First model version

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "./models/OPT/opt-1.3b",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 8192,
+  "hidden_size": 2048,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "use_cache": false,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 2048
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.26.0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a99668e2f43d0bc2ea538dc56ee5b6a9a3193fb6ea44bd8378f119ba616da8e
+size 10526299041

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02644fb7ade4ef5113bbe747c51459115e68eecf41f36a62a88a9f8c8be64afc
+size 5263162257

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e0956de6390e858565f3e0e7eb7ec59770d049540a033a0a8ddd00bf2170575
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc95b508acc43782ce53498e0ad90507a699c09b1452ef7ccf2e247b7d5df105
+size 623

trainer_state.json

@@ -0,0 +1,88 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.8036913731674553,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 7.78816199376947e-06,
+      "loss": 1.962,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.557632398753894e-05,
+      "loss": 0.7774,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.9626168224299065e-05,
+      "loss": 0.7326,
+      "step": 1500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.8760816891658016e-05,
+      "loss": 0.6961,
+      "step": 2000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.7895465559016964e-05,
+      "loss": 0.6348,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.7030114226375908e-05,
+      "loss": 0.6088,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.616476289373486e-05,
+      "loss": 0.5995,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.5299411561093806e-05,
+      "loss": 0.6067,
+      "step": 4000
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1.4434060228452753e-05,
+      "loss": 0.5517,
+      "step": 4500
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.3568708895811699e-05,
+      "loss": 0.4912,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.2703357563170648e-05,
+      "loss": 0.4921,
+      "step": 5500
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 1.1838006230529595e-05,
+      "loss": 0.4947,
+      "step": 6000
+    }
+  ],
+  "max_steps": 12840,
+  "num_train_epochs": 6,
+  "total_flos": 3.5783067431981875e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eda971994eab2365d709b36816efa694f433c58c2849c619cbd44c66f87a171a
+size 3503