Training in progress, step 40, checkpoint

last-checkpoint/model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44ab72b4709d6ffbeb35af35f341004d363c90fd1eda36628e6d84de407c80bf
+oid sha256:6533a9e99812f3baa1eca3103e64effd322cfbc0a0c2faedcdc2f3d1320dcd1d
 size 4976698672

last-checkpoint/model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ab6f792622c0c35fd0799cc8a9d4255063a06471fff7aa9c635e67635f7286f
+oid sha256:9cd12f2a551cb951ebf515ed0efbfdadcb44ecd151abf5ee08f73ab3c1a74c3b
 size 4999802720

last-checkpoint/model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:567bbc43b31b395b0d27e12f1dc5930e0dafe7f7b99b4e60685919b90587ae4c
+oid sha256:d883050650a869e5842b17c2b0b5a6645fa560483206c27dff4f6916eb1f59c5
 size 4915916176

last-checkpoint/model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75e3a8fbbb21272764f003e8b4f7a98ed04d0de1487f3c39a257ca07988b0161
+oid sha256:4ee7c9253ad2ba69db51ec8a088cdad179b0b5098768ddaa8b3d7f0cb161bf29
 size 1168138808

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b5fa7e25560e0e69c7447925bbecf06781cddc7ad3a142309b7ea1097dbfd80
+oid sha256:90ef2d5edf88d47c6b9060737b11660e2febbfcd57608a0514d9235edabc3c5a
 size 16311821124

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f60241cb6cb86cf9966e8cfe2248be00bce643b5808e2c3b78c9cb618eea253
+oid sha256:dc88fb92d712b475d32be3d1ada8ec5320caecbc5bee07323ed8ad65bd7eca3f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e76feebe960d60536ad1ed0bcaee2e12a3f8432f33b7ee3b0cae559b12130c0
+oid sha256:20d28c1500c52bfe18425b4bed2ac7a058807aa679eb235e2858e4c59d93c46b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f5988c600823ef881ed3900c9909420e69870efab70abf3dca0673a3c88b057
+oid sha256:0cef6593c9f9ee2d65b822806f53981afe9f4e72293b225f0334e12cac10ae5c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7090a3c6759641db81e3ee589636615551bb1b7ce0948f2fd4ab7d7beb35de9c
+oid sha256:295a7f74fd8125d4af9e8f677f10a9107aa9a572a3832d0bb0378329494588ed
 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": 0.2127659574468085,
+  "epoch": 0.425531914893617,
   "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": 50.508,
       "eval_steps_per_second": 6.326,
       "step": 20
+    },
+    {
+      "epoch": 0.3191489361702128,
+      "grad_norm": 6.875,
+      "learning_rate": 0.00019994532573409262,
+      "loss": 2.4864,
+      "step": 30
+    },
+    {
+      "epoch": 0.425531914893617,
+      "grad_norm": 7.84375,
+      "learning_rate": 0.00019950829025450114,
+      "loss": 2.6708,
+      "step": 40
+    },
+    {
+      "epoch": 0.425531914893617,
+      "eval_loss": 2.5071871280670166,
+      "eval_runtime": 46.4512,
+      "eval_samples_per_second": 32.314,
+      "eval_steps_per_second": 4.047,
+      "step": 40
     }
   ],
   "logging_steps": 10,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4755282835996672e+16,
+  "total_flos": 2.9510565671993344e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null