Training in progress, step 12000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:172b83ee8c0c178fc631d554a3d8e1a9ee973cecb6292c8a65ea9cf6b9413a5f
+oid sha256:38983cc6baa199b78ad222dae4c477c4bd0c63e2458372366630348ee28383b5
 size 579824888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bb1ba220a967824aa67b3f408cb2411ac14a2a8f57c220950876c97a9607f93
+oid sha256:7fd8341a68b63315868b34bd0e54e5f6c54b4a66537f640753aed597e0d3b48d
 size 1159794763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62b01f9ae52b370a3c5177e3cbec51226c2ec58f411c1ee0496cca95d179b183
+oid sha256:4d31404d4c654929d8c8604a09997c74ec2ccd4b35e0d5562c9b8d160dc81e06
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:687c619a9c245be775b1ee059ceaff574f576584c143ed02ddcab0296c87f35b
+oid sha256:51b5657716e2096af61b1cdab76b9fd3dc4ab393f10b4ad41400692973ae8e3f
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2,
+  "epoch": 0.24,
   "eval_steps": 1000,
-  "global_step": 10000,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -798,6 +798,164 @@
       "eval_samples_per_second": 307.239,
       "eval_steps_per_second": 19.311,
       "step": 10000
+    },
+    {
+      "epoch": 0.202,
+      "grad_norm": 0.18158847093582153,
+      "learning_rate": 0.0009048970918589055,
+      "loss": 3.607147521972656,
+      "step": 10100
+    },
+    {
+      "epoch": 0.204,
+      "grad_norm": 0.15705344080924988,
+      "learning_rate": 0.0009030403007569094,
+      "loss": 3.5972610473632813,
+      "step": 10200
+    },
+    {
+      "epoch": 0.206,
+      "grad_norm": 0.18561947345733643,
+      "learning_rate": 0.0009011675024148955,
+      "loss": 3.5994192504882814,
+      "step": 10300
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.17375363409519196,
+      "learning_rate": 0.0008992787712133476,
+      "loss": 3.592384948730469,
+      "step": 10400
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.14704184234142303,
+      "learning_rate": 0.0008973741821655428,
+      "loss": 3.5763116455078126,
+      "step": 10500
+    },
+    {
+      "epoch": 0.212,
+      "grad_norm": 0.1663106381893158,
+      "learning_rate": 0.0008954538109145713,
+      "loss": 3.59366455078125,
+      "step": 10600
+    },
+    {
+      "epoch": 0.214,
+      "grad_norm": 0.15191592276096344,
+      "learning_rate": 0.0008935177337303337,
+      "loss": 3.5883197021484374,
+      "step": 10700
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.15566915273666382,
+      "learning_rate": 0.0008915660275065107,
+      "loss": 3.5549887084960936,
+      "step": 10800
+    },
+    {
+      "epoch": 0.218,
+      "grad_norm": 0.17490389943122864,
+      "learning_rate": 0.0008895987697575093,
+      "loss": 3.558960266113281,
+      "step": 10900
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.17277678847312927,
+      "learning_rate": 0.0008876160386153846,
+      "loss": 3.5671484375,
+      "step": 11000
+    },
+    {
+      "epoch": 0.22,
+      "eval_accuracy": 0.3558709927196726,
+      "eval_loss": 3.554290771484375,
+      "eval_runtime": 6.8937,
+      "eval_samples_per_second": 281.559,
+      "eval_steps_per_second": 17.697,
+      "step": 11000
+    },
+    {
+      "epoch": 0.222,
+      "grad_norm": 0.15808428823947906,
+      "learning_rate": 0.0008856179128267363,
+      "loss": 3.578575439453125,
+      "step": 11100
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.14474111795425415,
+      "learning_rate": 0.0008836044717495819,
+      "loss": 3.5772747802734375,
+      "step": 11200
+    },
+    {
+      "epoch": 0.226,
+      "grad_norm": 0.1413886845111847,
+      "learning_rate": 0.0008815757953502035,
+      "loss": 3.556199645996094,
+      "step": 11300
+    },
+    {
+      "epoch": 0.228,
+      "grad_norm": 0.1502675712108612,
+      "learning_rate": 0.0008795319641999735,
+      "loss": 3.570118103027344,
+      "step": 11400
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.1517445147037506,
+      "learning_rate": 0.0008774730594721534,
+      "loss": 3.5563198852539064,
+      "step": 11500
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.16406166553497314,
+      "learning_rate": 0.0008753991629386706,
+      "loss": 3.5616604614257814,
+      "step": 11600
+    },
+    {
+      "epoch": 0.234,
+      "grad_norm": 0.14764074981212616,
+      "learning_rate": 0.0008733103569668701,
+      "loss": 3.5495458984375,
+      "step": 11700
+    },
+    {
+      "epoch": 0.236,
+      "grad_norm": 0.17058512568473816,
+      "learning_rate": 0.0008712067245162439,
+      "loss": 3.5244882202148435,
+      "step": 11800
+    },
+    {
+      "epoch": 0.238,
+      "grad_norm": 0.16127121448516846,
+      "learning_rate": 0.0008690883491351356,
+      "loss": 3.5396826171875,
+      "step": 11900
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.14211590588092804,
+      "learning_rate": 0.0008669553149574224,
+      "loss": 3.522979431152344,
+      "step": 12000
+    },
+    {
+      "epoch": 0.24,
+      "eval_accuracy": 0.3578128166428224,
+      "eval_loss": 3.5307533740997314,
+      "eval_runtime": 6.6725,
+      "eval_samples_per_second": 290.897,
+      "eval_steps_per_second": 18.284,
+      "step": 12000
     }
   ],
   "logging_steps": 100,
@@ -817,7 +975,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.919960866816e+17,
+  "total_flos": 4.7039530401792e+17,
   "train_batch_size": 120,
   "trial_name": null,
   "trial_params": null