Training in progress, step 40, checkpoint

last-checkpoint/model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ee32f36b7900d902a899b7c28c1e747b61dfe8e032393f18b0db55f93f613d3
+oid sha256:268996d6a7b89ae0f29dde4a67398cf04f727ed3e28393714d6df5af4ff1f0f5
 size 4938985352

last-checkpoint/model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:857c261e2ea2c6878716a55551c8c75b76190a9b4acd800ff7abc2fae5326de6
+oid sha256:de7e706d7e3f9d74ce4e683a82398a350d2ff6625c6056aa6a47be7a52bbcef2
 size 4947390880

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbd063d210cf1ed3f44b1b6355fdf3bae063911790a0a47ce34dd67237d0bc43
+oid sha256:8398f26be1335fd494b46970ebe464e368426e60743c23222af55e492baab031
 size 3590488816

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9e5f827cca92089963b50d61797ff6ee03c4d625d253f21e07aea047b3aab7a
+oid sha256:2a55afd7d953d6726c6fe91f71198d7c9b43989ac82a7472593f46beba082ba9
 size 13687759344

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:e3d7496cd5cad5fcd343f51f06f864ca525a833da3ba71e9c4d90915510423ac
+oid sha256:572996e9dc190ff3f3a6efdf58de929f593fa2dd2f97d74fed7646828651b17f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18518518518518517,
+  "epoch": 0.37037037037037035,
   "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": 56.74,
       "eval_steps_per_second": 7.107,
       "step": 20
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 1.5390625,
+      "learning_rate": 0.0002,
+      "loss": 1.7007,
+      "step": 30
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 1.984375,
+      "learning_rate": 0.00019984815164333163,
+      "loss": 1.8416,
+      "step": 40
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "eval_loss": 1.7034589052200317,
+      "eval_runtime": 42.8326,
+      "eval_samples_per_second": 35.043,
+      "eval_steps_per_second": 4.389,
+      "step": 40
     }
   ],
   "logging_steps": 10,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2990566673416192e+16,
+  "total_flos": 2.5981133346832384e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null