Training in progress, step 100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6e10bf400529e94f432815385ce44f8e973a32eec3c9be3ec7acb4befb5dddb
+oid sha256:c914af7e4717984588deb34667879d37816d8425bf9f40c7f2df62411adc325a
 size 4140280

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d025fb3332edbb7be7f811c4700970dac0a63ff9085905c32fab3d64583bd4c1
+oid sha256:cdc464916d664a581b71258bf99ebb2222699eaaa0da313672b893849e7b1439
 size 4291766

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d808c6b7b18375173160ea5614f4474ba68bfdb4e4128fb96aa9c3edc2450cb
+oid sha256:59eee07bd5257f958aa60b64ac056e06d5604ea0d6c7521294725ae674846323
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df89f21b55b2d65718ed1d2cdeadc1ff16958bc5f6ac66f1e557ef70c9dfe8e2
+oid sha256:92988225811cf70cd61cd7d96e2bd0c8a70a967dcaeff9b55ab11c5ec2a94a37
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de0d61bbd2d2279b9ea09ac3613573a205fb5f5a279324183ce6c23ca8fbac77
+oid sha256:33e17e9167c2b26888279edafd14d8478d0b5f19f0ac7a69f38e330c1bfc3f9e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aec03eba7d44b82e794b52483557f97fad5167bb70a3cf0811cfd3a0a2764f32
+oid sha256:0076df514a83103b8edf9019ff4243b312de59093a4c3eeb091b54a1aa048eb7
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c420644371984c0c279fff13e73e1c3067315dc564ce90ee02e2ca237d8a9e35
+oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 13.333333333333334,
+  "epoch": 16.666666666666668,
   "eval_steps": 20,
-  "global_step": 80,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -103,6 +103,28 @@
       "eval_samples_per_second": 640.486,
       "eval_steps_per_second": 5.12,
       "step": 80
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 0.46484375,
+      "learning_rate": 5.418275829936537e-06,
+      "loss": 9.9122,
+      "step": 90
+    },
+    {
+      "epoch": 16.666666666666668,
+      "grad_norm": 0.462890625,
+      "learning_rate": 0.0,
+      "loss": 9.9115,
+      "step": 100
+    },
+    {
+      "epoch": 16.666666666666668,
+      "eval_loss": 9.921339988708496,
+      "eval_runtime": 2.3434,
+      "eval_samples_per_second": 640.535,
+      "eval_steps_per_second": 5.121,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -117,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 131490423767040.0,
+  "total_flos": 164363029708800.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null