Training in progress, step 32200, checkpoint

last-checkpoint/README.md

@@ -1303,6 +1303,10 @@ You can finetune this model on your own dataset.
 | 0.5637 | 31900 | 0.2994        |
 | 0.5646 | 31950 | 0.3219        |
 | 0.5655 | 32000 | 0.2902        |
+| 0.5663 | 32050 | 0.3896        |
+| 0.5672 | 32100 | 0.2491        |
+| 0.5681 | 32150 | 0.2663        |
+| 0.5690 | 32200 | 0.3433        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cea8950aa6683070e22c1a564e52123795831f72f71fb839c14d7de92ee17a17
+oid sha256:059e5ea13c385fd2b7824c1ae9f5d7517f93ed2064e18f707d204b5f00551fcf
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ac2571e8a99f96a6e948efc2acbf6f064d1c41ef24c68243b8bfa9248b61bef
+oid sha256:3628f48729b03521592b21ba8e241dd8f7b12c27ab2d17f87975f425eeac02df
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea96a97725aec5e3c937ef8955386071fe1d87cf2432c4445ce113e85618ebef
+oid sha256:50d8e0757ed6c29dd6ad40d6348476d9c45a6c913dbe6d558683a2aff7f6eeaa
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b78f9ce48aa6920e09eb307b60e2b49742b779f95ad33075f31c6652ec108e55
+oid sha256:05d2345a7bbddb12fb6a365e62bd73e47296785a601a5379725821a73d3794f3
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6de4d7315ff5e38fd38a2be7f1976197684b731feeef6561c2bf9fe182bd3b1
+oid sha256:dfe5ee6b9c7e51d497fade31af9f8cbe420701d187e60d0b9c360cfa22b492c4
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5654609390185719,
+  "epoch": 0.568995069887438,
   "eval_steps": 500,
-  "global_step": 32000,
+  "global_step": 32200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4488,6 +4488,34 @@
       "learning_rate": 2.4152284463293475e-05,
       "loss": 0.2902,
       "step": 32000
+    },
+    {
+      "epoch": 0.5663444717357884,
+      "grad_norm": 2.785452365875244,
+      "learning_rate": 2.4103198444954943e-05,
+      "loss": 0.3896,
+      "step": 32050
+    },
+    {
+      "epoch": 0.5672280044530049,
+      "grad_norm": 2.5383968353271484,
+      "learning_rate": 2.4054112426616404e-05,
+      "loss": 0.2491,
+      "step": 32100
+    },
+    {
+      "epoch": 0.5681115371702214,
+      "grad_norm": 1.584861397743225,
+      "learning_rate": 2.4005026408277866e-05,
+      "loss": 0.2663,
+      "step": 32150
+    },
+    {
+      "epoch": 0.568995069887438,
+      "grad_norm": 1.5586644411087036,
+      "learning_rate": 2.395594038993933e-05,
+      "loss": 0.3433,
+      "step": 32200
     }
   ],
   "logging_steps": 50,