Training in progress, step 44400, checkpoint

last-checkpoint/README.md

@@ -1403,6 +1403,10 @@ You can finetune this model on your own dataset.
 | 0.7793 | 44100 | 0.2785        |
 | 0.7802 | 44150 | 0.2386        |
 | 0.7810 | 44200 | 0.3297        |
+| 0.7819 | 44250 | 0.2576        |
+| 0.7828 | 44300 | 0.2678        |
+| 0.7837 | 44350 | 0.3625        |
+| 0.7846 | 44400 | 0.311         |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c93ea012da084e7db255bf5307a12bc622616de2b559e1ebc270e29e3930b53
+oid sha256:0590fb55aab08f3535397ce8dcef99c8680506c32302ba2d6e910a8249da6224
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fc375ce7c64e73dfae981ff1f0ee30f111e70f92ece0482506acc2e5c8b7278
+oid sha256:abff80a73aec9612ce24bcd8cc146093b60dfe7bfd2e43a1f500d834e46d5802
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc4603f12b61034f467c4243e5cacbd3dc08f83f508811af862a64abae5532b6
+oid sha256:8eb5618265930c1ad5f9342c3f992eaed8023f41d629ef3773582c7b22437a29
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:086b678b22870553eb0c5be0c61abb20b7fa45eb12fa31835cd26537ecba1df1
+oid sha256:f9756468f8fd1e049c0f34546e465c8cf6b5e4ecebc81c7ebf057569a23c46ac
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af3f862129fa543cfe43517f44ed73b2bfc19062f029765e9ae1e7d6bb4162f5
+oid sha256:cdfed137404ca82aee02dc12b81b45bc0fb558d702987085b73e2f3d6d8e8b76
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7810429220194024,
+  "epoch": 0.7845770528882684,
   "eval_steps": 500,
-  "global_step": 44200,
+  "global_step": 44400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6196,6 +6196,34 @@
       "learning_rate": 1.2181186310891207e-05,
       "loss": 0.3297,
       "step": 44200
+    },
+    {
+      "epoch": 0.7819264547366189,
+      "grad_norm": 1.0489422082901,
+      "learning_rate": 1.213210029255267e-05,
+      "loss": 0.2576,
+      "step": 44250
+    },
+    {
+      "epoch": 0.7828099874538355,
+      "grad_norm": 2.2906908988952637,
+      "learning_rate": 1.2083014274214133e-05,
+      "loss": 0.2678,
+      "step": 44300
+    },
+    {
+      "epoch": 0.783693520171052,
+      "grad_norm": 1.5887507200241089,
+      "learning_rate": 1.2033928255875597e-05,
+      "loss": 0.3625,
+      "step": 44350
+    },
+    {
+      "epoch": 0.7845770528882684,
+      "grad_norm": 1.592004418373108,
+      "learning_rate": 1.1984842237537062e-05,
+      "loss": 0.311,
+      "step": 44400
     }
   ],
   "logging_steps": 50,