Training in progress, step 40, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9a1b5fe74d30a2b57275019644a375677da441d563a6cd3de6fb409ded03f62
+oid sha256:2f9505cbd1c71fa03bd7aa6e5610584fea463e8693b50cfc26ffa5e5d5e8ecb5
 size 4956450288

last-checkpoint/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77f31d93e3f4bb89019d604b40346ff6e1fc555bbf740c89dc528ba7e5a1fa13
+oid sha256:294e49d4e0151ff6ea8c7ae8fd3c7f751742dba5dc1a599b0003c7da1dee4b1d
 size 1214366696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4ffc2a19903049d433ee79e54f725e3f6a735e76cfecc66c0f6c64d4acad3d3
+oid sha256:c3a13208817ea46f3bf98ef16495ccb741166331a2537849f5b45e1362c03504
 size 6269038402

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f60241cb6cb86cf9966e8cfe2248be00bce643b5808e2c3b78c9cb618eea253
+oid sha256:e50d39405d88591ce6aca8b0b6c85c11b2a2f5ebf7c013d70f25e4f52dc10862
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e76feebe960d60536ad1ed0bcaee2e12a3f8432f33b7ee3b0cae559b12130c0
+oid sha256:ece10f667957ef7fe2aeebd2123f03c13fd50eecfc57b402ef932838893258f0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f5988c600823ef881ed3900c9909420e69870efab70abf3dca0673a3c88b057
+oid sha256:6e6f1c8eecc99beebe49ddacdcfb6d698bb3dc1d6bf171871581f2a9a4940bf9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7090a3c6759641db81e3ee589636615551bb1b7ce0948f2fd4ab7d7beb35de9c
+oid sha256:6933fdb81e79fb8d8cc03a2704a76076a84a3f1eeb0cb38a2be16ab7ccf10ff9
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86a562280f18454416a11d2a32a1435679f44d10b11637c5297815c06d499163
+oid sha256:9248d7f262b73b7b212e6bf7f6f66a12efea2182db378d6a810b44dc89e3400f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5405405405405406,
+  "epoch": 1.0810810810810811,
   "eval_steps": 20,
-  "global_step": 20,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 70.294,
       "eval_steps_per_second": 3.559,
       "step": 20
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 1.515625,
+      "learning_rate": 0.00019994532573409262,
+      "loss": 1.9936,
+      "step": 30
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 4.625,
+      "learning_rate": 0.00019950829025450114,
+      "loss": 1.8595,
+      "step": 40
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "eval_loss": 2.112858772277832,
+      "eval_runtime": 21.4411,
+      "eval_samples_per_second": 70.006,
+      "eval_steps_per_second": 3.545,
+      "step": 40
     }
   ],
   "logging_steps": 10,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3638567716716544e+16,
+  "total_flos": 2.727713543343309e+16,
   "train_batch_size": 5,
   "trial_name": null,
   "trial_params": null