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:a32226883a7ac50cf6cdbc8be3102d173e1907b7a8ed2376557a3d33d01b2367
+oid sha256:819656ffe3859b406da1139fedb26c50f97ce2b4edb13ca208b7b4c62733df41
 size 4943162336

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c09202edeafe5745b96094f13f01f5c2116e51dae7201eff329f3fbb73d0b219
+oid sha256:98d128e71fd090cba0c2c7526d33b187b4ee7142516dce2efc0a82670ea89fa6
 size 4999819336

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f80cb8df7b71b0e9b29b59e5f6dc8c04ccc38c0d087aaaba76e08b2a6df8cb58
+oid sha256:cdfe0ce064aea90d87a757a148352d7662d83ca04a21768c9381ea479da81f16
 size 4540516344

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8144c06cc4e463d75d11b2c6eee14c47522fe31b4d94c4b73d58f0e4ca64e80
+oid sha256:e356b933140462b03f88463ba5fc29f472af721719bae7fff1d176e6dc573a67
 size 14710121812

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": 0.19047619047619047,
+  "epoch": 0.38095238095238093,
   "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": 55.745,
       "eval_steps_per_second": 6.982,
       "step": 20
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 58.0,
+      "learning_rate": 0.0002,
+      "loss": 8.874,
+      "step": 30
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 234.0,
+      "learning_rate": 0.00019984815164333163,
+      "loss": 9.542,
+      "step": 40
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "eval_loss": 11.596774101257324,
+      "eval_runtime": 47.0413,
+      "eval_samples_per_second": 31.908,
+      "eval_steps_per_second": 3.996,
+      "step": 40
     }
   ],
   "logging_steps": 10,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3980127138414592e+16,
+  "total_flos": 2.7960254276829184e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null