Training in progress, step 34200, checkpoint

last-checkpoint/README.md

@@ -1197,6 +1197,10 @@ You can finetune this model on your own dataset.
 | 0.5990 | 33900 | 0.2361        |
 | 0.5999 | 33950 | 0.4459        |
 | 0.6008 | 34000 | 0.3169        |
+| 0.6017 | 34050 | 0.3146        |
+| 0.6026 | 34100 | 0.3125        |
+| 0.6035 | 34150 | 0.2738        |
+| 0.6043 | 34200 | 0.3062        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:864337e54b0d99195a63884a96e6fc0a3ba7ad47ef988a3eb797527a137e5a93
+oid sha256:1bdca6c44be34b9e69175940da4b56167b7928c9d214c258d43c5b620bc91b46
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fb36dbae403fd4e5ed4b762c80bac9104bf77e8de0d5c4f5e8c6eaad4c7e78a
+oid sha256:3e8cce5c0114dfe6db2b221097701d4f63da8b0269ca76f1850aa97156719ebf
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5828bcbe6e1a072cf5e6743b55a27970aa81f22da119739e72fdd503508aec8
+oid sha256:ed40b835a3a95c0d5caa9e2f9ac60fe5821207cfed755931f0a4c6a4e1bc7f9c
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ca4bb4a820d3aea8a0a082f1aadfd9af93af513ae74063f47c2633f52672d6e
+oid sha256:62c9791c94ed19713d54c258fa73c1747c3a24c92cf2d0108a3b66f313c783e0
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bf428199bdc10b835fdf8661e7d1632cc44c4e8393f3c5779cb4131e9a11ef8
+oid sha256:67100c483c5008bb6cb432330fcbe9399cb2dfd8372d624a774af533d43e3106
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6008022477072326,
+  "epoch": 0.6043363785760987,
   "eval_steps": 500,
-  "global_step": 34000,
+  "global_step": 34200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4768,6 +4768,34 @@
       "learning_rate": 2.218982545011879e-05,
       "loss": 0.3169,
       "step": 34000
+    },
+    {
+      "epoch": 0.6016857804244491,
+      "grad_norm": 1.1555734872817993,
+      "learning_rate": 2.2140739431780252e-05,
+      "loss": 0.3146,
+      "step": 34050
+    },
+    {
+      "epoch": 0.6025693131416656,
+      "grad_norm": 1.4827885627746582,
+      "learning_rate": 2.2091653413441717e-05,
+      "loss": 0.3125,
+      "step": 34100
+    },
+    {
+      "epoch": 0.6034528458588821,
+      "grad_norm": 1.5724104642868042,
+      "learning_rate": 2.204256739510318e-05,
+      "loss": 0.2738,
+      "step": 34150
+    },
+    {
+      "epoch": 0.6043363785760987,
+      "grad_norm": 1.5903054475784302,
+      "learning_rate": 2.1993481376764643e-05,
+      "loss": 0.3062,
+      "step": 34200
     }
   ],
   "logging_steps": 50,