Training in progress, step 35000, checkpoint

last-checkpoint/README.md

@@ -1213,6 +1213,10 @@ You can finetune this model on your own dataset.
 | 0.6132 | 34700 | 0.3007        |
 | 0.6141 | 34750 | 0.3932        |
 | 0.6149 | 34800 | 0.3           |
+| 0.6158 | 34850 | 0.2785        |
+| 0.6167 | 34900 | 0.3015        |
+| 0.6176 | 34950 | 0.3291        |
+| 0.6185 | 35000 | 0.2634        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78346a0c56430d22fa1490f284416b4aeee8fb9539989a398220c805d75e2e61
+oid sha256:0d79a423fd264f8aac56fd95502b2264a968c0f7cf7b4c2a1c6541772551d3d3
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:332311a89c1a8130797191a2ad7878850bf8a5f8687fb07aa8ce26dd6bf3aca2
+oid sha256:3a70db7a09d43a45af8ba846e6b88322513995922a372c0450b6f22318eba386
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:663998c1aaed54adecb3878007dbade857c46ba6a1c5eaffb67717a822135458
+oid sha256:b5dbdbbf596351fb268b717a3c2006112ba85ad19e4243b93a29f0071121e106
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:480efcc1d108b2db853c5d91deb1ed2fd305f7b9cbbdf50854f3a85cc79a1117
+oid sha256:33dd792f68c210603692aedada855793ed50b3aa941307b551dc822363f2d043
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e917b101e0be67dbb3890bb4d8dceac22ecd3870c266a2b20cb6488727437a58
+oid sha256:1ba7705125f055257ca9fb00bd8484394e209b5a6e280efe9550fda932420046
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6149387711826969,
+  "epoch": 0.618472902051563,
   "eval_steps": 500,
-  "global_step": 34800,
+  "global_step": 35000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4880,6 +4880,34 @@
       "learning_rate": 2.1405430877068978e-05,
       "loss": 0.3,
       "step": 34800
+    },
+    {
+      "epoch": 0.6158223038999134,
+      "grad_norm": 1.4415560960769653,
+      "learning_rate": 2.135634485873044e-05,
+      "loss": 0.2785,
+      "step": 34850
+    },
+    {
+      "epoch": 0.61670583661713,
+      "grad_norm": 1.8688596487045288,
+      "learning_rate": 2.1307258840391904e-05,
+      "loss": 0.3015,
+      "step": 34900
+    },
+    {
+      "epoch": 0.6175893693343465,
+      "grad_norm": 3.085685968399048,
+      "learning_rate": 2.125817282205337e-05,
+      "loss": 0.3291,
+      "step": 34950
+    },
+    {
+      "epoch": 0.618472902051563,
+      "grad_norm": 1.3053193092346191,
+      "learning_rate": 2.120908680371483e-05,
+      "loss": 0.2634,
+      "step": 35000
     }
   ],
   "logging_steps": 50,