Training in progress, step 44200, checkpoint

last-checkpoint/README.md

@@ -1399,6 +1399,10 @@ You can finetune this model on your own dataset.
 | 0.7757 | 43900 | 0.3049        |
 | 0.7766 | 43950 | 0.2939        |
 | 0.7775 | 44000 | 0.2909        |
+| 0.7784 | 44050 | 0.2157        |
+| 0.7793 | 44100 | 0.2785        |
+| 0.7802 | 44150 | 0.2386        |
+| 0.7810 | 44200 | 0.3297        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12bbe29ea94a2a3e248956e4ad4f48429053ec1581ede3091505ee45e42c209e
+oid sha256:3c93ea012da084e7db255bf5307a12bc622616de2b559e1ebc270e29e3930b53
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc95281118678bfa685a8fa9d0f9c2b4de3f7f9c764726219c4efe80cd17496a
+oid sha256:0fc375ce7c64e73dfae981ff1f0ee30f111e70f92ece0482506acc2e5c8b7278
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2248c4c2662777880f6435205956f86ee9cef13d01a64d9b6e6e97f9ff29c8a6
+oid sha256:bc4603f12b61034f467c4243e5cacbd3dc08f83f508811af862a64abae5532b6
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41c83ba4cca9cc14a64aa6c3e0597b81f5560663b8d07b1843663e365af550c1
+oid sha256:086b678b22870553eb0c5be0c61abb20b7fa45eb12fa31835cd26537ecba1df1
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:947d6bd91fa66a1fa64426daf31057323ec244470e03f87d8bca1497c127e637
+oid sha256:af3f862129fa543cfe43517f44ed73b2bfc19062f029765e9ae1e7d6bb4162f5
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7775087911505363,
+  "epoch": 0.7810429220194024,
   "eval_steps": 500,
-  "global_step": 44000,
+  "global_step": 44200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6168,6 +6168,34 @@
       "learning_rate": 1.2377530384245351e-05,
       "loss": 0.2909,
       "step": 44000
+    },
+    {
+      "epoch": 0.7783923238677528,
+      "grad_norm": 1.421271562576294,
+      "learning_rate": 1.2328444365906816e-05,
+      "loss": 0.2157,
+      "step": 44050
+    },
+    {
+      "epoch": 0.7792758565849693,
+      "grad_norm": 1.2172672748565674,
+      "learning_rate": 1.2279358347568279e-05,
+      "loss": 0.2785,
+      "step": 44100
+    },
+    {
+      "epoch": 0.7801593893021859,
+      "grad_norm": 1.5359545946121216,
+      "learning_rate": 1.2230272329229744e-05,
+      "loss": 0.2386,
+      "step": 44150
+    },
+    {
+      "epoch": 0.7810429220194024,
+      "grad_norm": 1.3057314157485962,
+      "learning_rate": 1.2181186310891207e-05,
+      "loss": 0.3297,
+      "step": 44200
     }
   ],
   "logging_steps": 50,