Training in progress, step 100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5252b2d702ec4e4b7629e26fe3a70c426d1c12a5b12acd3ae606f3a9754efaae
+oid sha256:b356afc6d082488f2555ef406378069504708e31271d6e086beee3c91f1f5c83
 size 662430992

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:242746371cb73d68846b644343062826e77803c4164e9556ac463d01ae95069f
+oid sha256:88b27e660c26757696366e20c37f079effc428107f2e9ffa74898f7f9b47361d
 size 674384884

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a50d87badb0708be06ac367c54fb94d34320d2eb8407fd57285a16c8da09911d
+oid sha256:c63e25c94fd32bbfac74e77e235933e40e71931ccdab4688693badf62fc9d895
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a55ac2f13f8b0b0932cc32ea158ca78aa103ef94c5e5ed92bad08a2b3d35ea4
+oid sha256:42d5a9f1444725574e6e96d7460d2ae867d4c9d4d70a147ad1691b8ce1c4b0b8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d244a3e1f8a0833f09ba072f66200d74bfe752b03372f6d7e2933c7d7641ba2
+oid sha256:86e844065e2ec1428132da97db98340b7020ef84b112f1abe984badffc1a1d8a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14926bd6988ebc984f858596410fe698400001fdebd5c125a448743474bdadad
+oid sha256:3774449d16a3fcd1d29aba215bc5841e6b8bc77f3a4c81e9a133c2a3c87bcc8d
 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": 11.428571428571429,
+  "epoch": 14.285714285714286,
   "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": 304.944,
       "eval_steps_per_second": 3.251,
       "step": 80
+    },
+    {
+      "epoch": 12.857142857142858,
+      "grad_norm": 2.046875,
+      "learning_rate": 5.418275829936537e-06,
+      "loss": 3.7097,
+      "step": 90
+    },
+    {
+      "epoch": 14.285714285714286,
+      "grad_norm": 1.6171875,
+      "learning_rate": 0.0,
+      "loss": 3.6947,
+      "step": 100
+    },
+    {
+      "epoch": 14.285714285714286,
+      "eval_loss": 3.0370891094207764,
+      "eval_runtime": 5.0102,
+      "eval_samples_per_second": 299.59,
+      "eval_steps_per_second": 3.194,
+      "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": 2.862844810887168e+16,
+  "total_flos": 3.57855601360896e+16,
   "train_batch_size": 24,
   "trial_name": null,
   "trial_params": null