Training in progress, step 60, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a6ebc6956166a08650fba840403d3b0a388a1247d71506f94c7f5b975c634f6
+oid sha256:2392bcb18cf6a8e1a05a1d93ca356ffd43cfb5139c9f132e4c34270f8b6835cc
 size 4995335576

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f5ee1a166922a716826463a6373347a9d247069e3ac46111221ae8dcdf642c8
+oid sha256:59f3a5c06cfe114b367ef79249b8fa1a476f4089babf7356b1705e36960af7f7
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae4b177f59982c88cd9a3aefdb3c7a2d89fb448f97dc7cc2078ccab25914c1c4
+oid sha256:d02dd6f18eb9beef1ba890d470e04ef8069a1d28c8636c6640b6e9693e3ac119
 size 6961290854

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc88fb92d712b475d32be3d1ada8ec5320caecbc5bee07323ed8ad65bd7eca3f
+oid sha256:dbbc0a86104f167e435d82d912099d9f4e8e28814d0b3054a66bc62faad66266
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20d28c1500c52bfe18425b4bed2ac7a058807aa679eb235e2858e4c59d93c46b
+oid sha256:ab9aca62c8968a97eee76d9db5ace24bd5602b66748ad8ebaa3c5beb481c0acd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cef6593c9f9ee2d65b822806f53981afe9f4e72293b225f0334e12cac10ae5c
+oid sha256:4ecef8be965f4a8a3ed32d79c73f9a4a9b6fc06e37821a549724a0a8e8322513
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:295a7f74fd8125d4af9e8f677f10a9107aa9a572a3832d0bb0378329494588ed
+oid sha256:a0d44c275e240e610f81071dc60b4fd4a20c4c4c06cc32abe80112f3f1a29d61
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:572996e9dc190ff3f3a6efdf58de929f593fa2dd2f97d74fed7646828651b17f
+oid sha256:e3671bd7fce476af6c5d68b2346a8d63f3c9e317781066d2c00973b04663cf26
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
+  "epoch": 1.5,
   "eval_steps": 20,
-  "global_step": 40,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,28 @@
       "eval_samples_per_second": 99.436,
       "eval_steps_per_second": 5.035,
       "step": 40
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.00019939306773179497,
+      "loss": 1.1096,
+      "step": 50
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 1.0,
+      "learning_rate": 0.00019863613034027224,
+      "loss": 1.0699,
+      "step": 60
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 2.048560619354248,
+      "eval_runtime": 14.1768,
+      "eval_samples_per_second": 105.877,
+      "eval_steps_per_second": 5.361,
+      "step": 60
     }
   ],
   "logging_steps": 10,
@@ -78,7 +100,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.2554433690730496e+16,
+  "total_flos": 4.889291985518592e+16,
   "train_batch_size": 5,
   "trial_name": null,
   "trial_params": null