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 sha256:828b20ace8b4c5a61ba76b2860edb800626265b55d001cd72b6bc1b1be7c9589
+oid sha256:1a6ebc6956166a08650fba840403d3b0a388a1247d71506f94c7f5b975c634f6
 size 4995335576

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3490a23c5609581c2f6a368aea3ff317a2f9144fcd91545748c65ee969ef73ec
+oid sha256:3f5ee1a166922a716826463a6373347a9d247069e3ac46111221ae8dcdf642c8
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cdafc8a427a078d2cbb5d45edb9cdae68256bd0930d38ce0b2d2a65a50c4a2d
+oid sha256:ae4b177f59982c88cd9a3aefdb3c7a2d89fb448f97dc7cc2078ccab25914c1c4
 size 6961290854

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": 0.5,
+  "epoch": 1.0,
   "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": 105.722,
       "eval_steps_per_second": 5.353,
       "step": 20
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.86328125,
+      "learning_rate": 0.0002,
+      "loss": 1.9109,
+      "step": 30
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.94921875,
+      "learning_rate": 0.00019984815164333163,
+      "loss": 1.9526,
+      "step": 40
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.8265540599822998,
+      "eval_runtime": 15.0951,
+      "eval_samples_per_second": 99.436,
+      "eval_steps_per_second": 5.035,
+      "step": 40
     }
   ],
   "logging_steps": 10,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6338486164455424e+16,
+  "total_flos": 3.2554433690730496e+16,
   "train_batch_size": 5,
   "trial_name": null,
   "trial_params": null