Training in progress, step 19200, checkpoint

last-checkpoint/README.md

@@ -1407,6 +1407,10 @@ You can finetune this model on your own dataset.
 | 0.3340 | 18900 | 0.2962        |
 | 0.3349 | 18950 | 0.3156        |
 | 0.3357 | 19000 | 0.3791        |
+| 0.3366 | 19050 | 0.3287        |
+| 0.3375 | 19100 | 0.4034        |
+| 0.3384 | 19150 | 0.3476        |
+| 0.3393 | 19200 | 0.363         |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:123a3c7e068975f2d73a559688da89498d96c9f5f3906b2f60a8f55923c134f5
+oid sha256:df4767c3af86ada5d64ec1e82bd26678813b4adc76a3a64ed02773659cbd3a1c
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e186b88037a18eebc7b613039df85cfc79c02be57538ce16444dea0485fdf79
+oid sha256:22ccaf4e0b9685757c9b442e5d71f5cf29896d66f4cfd0e1ebce8fda1955c2b6
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03af62e0682690ebbb7904f13bcb54bda8192bd3193a8746111a4da158c48b8c
+oid sha256:ed10afe606c6f5f77149b4d46e00c2aeeaae1b1caab0bfc6ff1ecf5b3e7db240
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10840146a6e19998f1fdbf028a41f37469dd8a3b8988531196e63b1251245096
+oid sha256:313b190fc264431dd211e2e439d1b10b0d124518229dd39cd606069f801f643f
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23958946bfe31c250bee11672fccb9ed52902b5ac707ac8090942157c16267c1
+oid sha256:e48deb26910c4a97c1b79325c939cfd44618a0d9f9449782152989a93c937ce2
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.33574243254227704,
+  "epoch": 0.3392765634111431,
   "eval_steps": 500,
-  "global_step": 19000,
+  "global_step": 19200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2668,6 +2668,34 @@
       "learning_rate": 3.69097406294791e-05,
       "loss": 0.3791,
       "step": 19000
+    },
+    {
+      "epoch": 0.33662596525949356,
+      "grad_norm": 1.4146838188171387,
+      "learning_rate": 3.6860654611140565e-05,
+      "loss": 0.3287,
+      "step": 19050
+    },
+    {
+      "epoch": 0.3375094979767101,
+      "grad_norm": 1.640153169631958,
+      "learning_rate": 3.681156859280202e-05,
+      "loss": 0.4034,
+      "step": 19100
+    },
+    {
+      "epoch": 0.3383930306939266,
+      "grad_norm": 1.670589804649353,
+      "learning_rate": 3.6762482574463494e-05,
+      "loss": 0.3476,
+      "step": 19150
+    },
+    {
+      "epoch": 0.3392765634111431,
+      "grad_norm": 3.375941753387451,
+      "learning_rate": 3.671339655612496e-05,
+      "loss": 0.363,
+      "step": 19200
     }
   ],
   "logging_steps": 50,