Training in progress, step 32600, checkpoint

last-checkpoint/README.md

@@ -1311,6 +1311,10 @@ You can finetune this model on your own dataset.
 | 0.5708 | 32300 | 0.2891        |
 | 0.5716 | 32350 | 0.296         |
 | 0.5725 | 32400 | 0.2478        |
+| 0.5734 | 32450 | 0.3514        |
+| 0.5743 | 32500 | 0.2741        |
+| 0.5752 | 32550 | 0.3546        |
+| 0.5761 | 32600 | 0.3927        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae7029cc4a936db82aecdfc345ae4f6be581e777c25d3e011d86f49807e6bd27
+oid sha256:45fd58276a613db39a02b73ae7fb0f916427f84c68306d47cd2dd77d778f740d
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffb5e77212890ce43c0fc7a397665bcd4da432ff88fa93a14b948bcf16b02cdd
+oid sha256:ad0c582d327743ee610c3253c0a4bdc5cb41fe46898db21b3b1c785e2413a4e9
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa682a307fc96e53a68118cb34dd8ebd33bebc1ee7d8a07cfe20e4ef67c0641e
+oid sha256:92457d32429f413543dc4a520ec7ff903eebfb5a9a30773f04a7c15eb4dca6c4
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7d183fbaa9612fc768da7cf7cefd13466b61ea27398ff0fc8e2f5977752f4ef
+oid sha256:dc7b96e3cd8fbcf40fa74eb52caa9f2570529a551c9001ee45b2d2020cedf149
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71836e8eeb9479ebd5deabd14069458b8ae082f80c2be8da5292f909ebf1971a
+oid sha256:afd2952fde33bc16ddb69c03104a4d42ffc3097dd2a6f3924f62735831aaadce
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.572529200756304,
+  "epoch": 0.5760633316251701,
   "eval_steps": 500,
-  "global_step": 32400,
+  "global_step": 32600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4544,6 +4544,34 @@
       "learning_rate": 2.3759596316585182e-05,
       "loss": 0.2478,
       "step": 32400
+    },
+    {
+      "epoch": 0.5734127334735205,
+      "grad_norm": 2.731212615966797,
+      "learning_rate": 2.371051029824665e-05,
+      "loss": 0.3514,
+      "step": 32450
+    },
+    {
+      "epoch": 0.574296266190737,
+      "grad_norm": 1.70058274269104,
+      "learning_rate": 2.366142427990811e-05,
+      "loss": 0.2741,
+      "step": 32500
+    },
+    {
+      "epoch": 0.5751797989079536,
+      "grad_norm": 3.394753932952881,
+      "learning_rate": 2.3612338261569576e-05,
+      "loss": 0.3546,
+      "step": 32550
+    },
+    {
+      "epoch": 0.5760633316251701,
+      "grad_norm": 2.7270805835723877,
+      "learning_rate": 2.356423396359781e-05,
+      "loss": 0.3927,
+      "step": 32600
     }
   ],
   "logging_steps": 50,