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:ebb73bcd3bf64d6b7f6c73f12411aa0002bd1ca75bb1ead942c50abb1c6a3d0c
+oid sha256:64a1b5af95246211699d2bb4b0bd220e2378ddf0436c028d8234cac8b1175407
 size 4939116424

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c41f1c577edc81dfba0f3ff054e62abf8cd77b5e10c7889383f2a475a793632
+oid sha256:e15c74793e993ea1a052252ea23effe0455192f6c1302ffbd55d2fe34f851c05
 size 4947390880

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ee7c8fa42eb9f6e68261d8b7c688e67c38f688f5d787e776948b6b4d41c503
+oid sha256:d811b7b26ec9ae2a0e64b1f56035a5510418077c16c6e7c651524d4210657e8d
 size 3590619888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96f45ab9d4a18d07fd3cbc3100fcdb3cd6de4c8ab8f76c5f6496ffac4a30b541
+oid sha256:9ede79028f2a31049e1da65c77dade050428d9be0ce749e96d1ff01479844cf3
 size 13688025584

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": 55.294,
       "eval_steps_per_second": 6.926,
       "step": 20
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 1.765625,
+      "learning_rate": 0.0002,
+      "loss": 1.8651,
+      "step": 30
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 1.5390625,
+      "learning_rate": 0.00019984815164333163,
+      "loss": 1.9748,
+      "step": 40
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "eval_loss": 1.8448469638824463,
+      "eval_runtime": 42.3761,
+      "eval_samples_per_second": 35.421,
+      "eval_steps_per_second": 4.436,
+      "step": 40
     }
   ],
   "logging_steps": 10,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2990695522435072e+16,
+  "total_flos": 2.5981391044870144e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null