Training in progress, step 60, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae4abc05650849fb84375c4b3c802c9c9c31dbfb9c6d98acc14dce8fe584f12d
+oid sha256:e77001dd01949849df6db7c281e4f173c2772a5c29a9acfcc0a291204cac94d7
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c62f06979cf820d1bc4612fea30f44881af3b0376093dca294382ee927a5438
+oid sha256:e7121aaf20e1078f0517c2a16980937c88f6dfbb0b414dd833b71f937a7e4b67
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62f5415ab0d082726880d0dd73d69a20743d20a0a7c951a4836c628ef156f744
+oid sha256:8cb4d60225d8c48e38a702d9643499b1191b9397c9d0952b41200b5d100ae38b
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d64f701370aa11c801b0e964ae533eec7ae3c3c8e7535246f28875affe1de61
+oid sha256:2aec0ba2a5c752d849e13597ae7bab4da49c31f7c4cd960e7c1948813502041f
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:572996e9dc190ff3f3a6efdf58de929f593fa2dd2f97d74fed7646828651b17f
+oid sha256:e3671bd7fce476af6c5d68b2346a8d63f3c9e317781066d2c00973b04663cf26
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.076923076923077,
+  "epoch": 4.615384615384615,
   "eval_steps": 40,
-  "global_step": 40,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -51,6 +51,20 @@
       "eval_samples_per_second": 284.862,
       "eval_steps_per_second": 4.555,
       "step": 40
+    },
+    {
+      "epoch": 3.8461538461538463,
+      "grad_norm": 0.3203125,
+      "learning_rate": 0.00019939306773179497,
+      "loss": 10.3159,
+      "step": 50
+    },
+    {
+      "epoch": 4.615384615384615,
+      "grad_norm": 0.32421875,
+      "learning_rate": 0.00019863613034027224,
+      "loss": 10.2518,
+      "step": 60
     }
   ],
   "logging_steps": 10,
@@ -70,7 +84,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 16366341980160.0,
+  "total_flos": 24549512970240.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null