Training in progress, step 44800, checkpoint

last-checkpoint/README.md

@@ -1411,6 +1411,10 @@ You can finetune this model on your own dataset.
 | 0.7863 | 44500 | 0.2602        |
 | 0.7872 | 44550 | 0.3936        |
 | 0.7881 | 44600 | 0.229         |
+| 0.7890 | 44650 | 0.3017        |
+| 0.7899 | 44700 | 0.2795        |
+| 0.7908 | 44750 | 0.279         |
+| 0.7916 | 44800 | 0.227         |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fce513425ee78d82ca94654cdc0a4320210e5ec028784be1406c877832c93919
+oid sha256:2970aabf3a655ac85113d5b6672798ff4b6430f64aad4045ed8ffd01109ee0a4
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:382cb2a8e601a053bb0ea3969b939edccc79edf806fa2fb79934a1132c941d31
+oid sha256:ce8b8c1496f83dcf4b7c667f04fccd67c7d43b788742223114f77d71b8b17910
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bf11240eaa3ac15b3a592742695066b7826256894b145544defe57b1a51d2f5
+oid sha256:fb56f2c027efc838c67094a45905db4a06a6d3525086412dec63fe94b6326cc5
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47e00c9999dcddbc2f016707d637f020dd9c8d184d501770291cf9d13b707305
+oid sha256:3d02bc78b22ccfd2d2cb2a9e32bb7cd76760001fe2e9b8f3babc4091b78fde49
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f34973fe7d7e41a1f8ad1f0f8cd4803fde065c5148acc0e939fcacd0a4b92d9
+oid sha256:8d1b4b34303310b51ebb01ce33c3b39156dd3c7f40c71fbb94511f9c8503c5fa
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7881111837571345,
+  "epoch": 0.7916453146260006,
   "eval_steps": 500,
-  "global_step": 44600,
+  "global_step": 44800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6252,6 +6252,34 @@
       "learning_rate": 1.1788498164182915e-05,
       "loss": 0.229,
       "step": 44600
+    },
+    {
+      "epoch": 0.788994716474351,
+      "grad_norm": 4.3157148361206055,
+      "learning_rate": 1.1739412145844378e-05,
+      "loss": 0.3017,
+      "step": 44650
+    },
+    {
+      "epoch": 0.7898782491915676,
+      "grad_norm": 1.8925341367721558,
+      "learning_rate": 1.1690326127505841e-05,
+      "loss": 0.2795,
+      "step": 44700
+    },
+    {
+      "epoch": 0.7907617819087841,
+      "grad_norm": 1.678846001625061,
+      "learning_rate": 1.1641240109167304e-05,
+      "loss": 0.279,
+      "step": 44750
+    },
+    {
+      "epoch": 0.7916453146260006,
+      "grad_norm": 1.3051953315734863,
+      "learning_rate": 1.1592154090828769e-05,
+      "loss": 0.227,
+      "step": 44800
     }
   ],
   "logging_steps": 50,