Training in progress, step 13200, checkpoint

last-checkpoint/README.md

@@ -1285,6 +1285,10 @@ You can finetune this model on your own dataset.
 | 0.2280 | 12900 | 0.3297        |
 | 0.2288 | 12950 | 0.4071        |
 | 0.2297 | 13000 | 0.4069        |
+| 0.2306 | 13050 | 0.5156        |
+| 0.2315 | 13100 | 0.4359        |
+| 0.2324 | 13150 | 0.3702        |
+| 0.2333 | 13200 | 0.5026        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a99dbe886ae3b48dcbc17c9add8a4bd329b9679468fb6c162134aa8463356d5
+oid sha256:0408532633e3d53818583ff9ef02c9be81d3ffdd069f1e604b4cdcf7a79bbd08
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:172018835a66c5e0120e97d48b6c921f1ef2ffa9a8cbf21cd65db32f82f39fdc
+oid sha256:6b0884b763c5d2ec8f0b94fd605e20d3981be5785da135173f386b90a4f72ddc
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0a97494fc3a06e5f40c026a0f41674c967ae21ee669dae8157fc95b5874a10f
+oid sha256:bff3c556549471e3b0bd6d9a3f96647cfb8a7aa9ac95f0e83191eb61af4e6bc0
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c530f7e876503d8e13ff43d14d04017a4f2689d24e141257ebdc42956b0bd010
+oid sha256:f0e926fae13271b40ac8f9ad92492b339eb4958bd5b878164fc6bd3383e8e0f9
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8a946928e63f8835465228f3f0df594649164b69e587f90a1cdfe3fc4f57565
+oid sha256:c897b83c9872ac7b716f5b64194b036c139fb3350016b3588f5f49c22a743418
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.22971850647629483,
+  "epoch": 0.23325263734516088,
   "eval_steps": 500,
-  "global_step": 13000,
+  "global_step": 13200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1828,6 +1828,34 @@
       "learning_rate": 4.279711766900316e-05,
       "loss": 0.4069,
       "step": 13000
+    },
+    {
+      "epoch": 0.23060203919351133,
+      "grad_norm": 1.8681453466415405,
+      "learning_rate": 4.2748031650664624e-05,
+      "loss": 0.5156,
+      "step": 13050
+    },
+    {
+      "epoch": 0.23148557191072786,
+      "grad_norm": 1.6242793798446655,
+      "learning_rate": 4.2698945632326096e-05,
+      "loss": 0.4359,
+      "step": 13100
+    },
+    {
+      "epoch": 0.23236910462794438,
+      "grad_norm": 2.897428035736084,
+      "learning_rate": 4.2649859613987554e-05,
+      "loss": 0.3702,
+      "step": 13150
+    },
+    {
+      "epoch": 0.23325263734516088,
+      "grad_norm": 1.855938196182251,
+      "learning_rate": 4.260077359564902e-05,
+      "loss": 0.5026,
+      "step": 13200
     }
   ],
   "logging_steps": 50,