Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b5fcf15bd242e44d655a57970dccb28a1a1a885e86a328e6fa1aebc857fd3a4
+oid sha256:dc9a0e2e05d9eacf5c069bd04337e5de4a41461f12fee894e25c6f74e61bcfb7
 size 37965300

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10227a4f65d2663111b9f64b91da210f6b75b6963c6c4f0f49d944588df122d4
+oid sha256:48f70a09efed6f9bfd0e89bcc03ed83843c149bc1a8aed4c526ce0e831f28eb8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb28a3fc3692f8f0c1809f96d2eac71d187e1ad52d0e32562154fe7cebd38ad2
+oid sha256:67e1ffba66ebd0baf2b920f9ae2738c8721a19b9723b342f2d169f123ca94ed3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b683c6a460493725dce6ad06952fcb9b8689ba835b925e253a89aa3fc3045b4e
+oid sha256:7339772db12266fe7eed955eb376a3a5e6df0199ef8f977071677928845bae76
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7394cb3c32f9e64c34f05b37af23c0d39c5b2b7b19c6b74deaabe63113dfde72
+oid sha256:922c1f6d2c32c0a328d51fb80e9b310682ef431fd00720c628f8cd031238583e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004397215097105167,
+  "epoch": 0.008794430194210334,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 43.414,
       "eval_steps_per_second": 5.436,
       "step": 3
+    },
+    {
+      "epoch": 0.005862953462806889,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.007328691828508612,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.008794430194210334,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.008794430194210334,
+      "eval_loss": NaN,
+      "eval_runtime": 26.6353,
+      "eval_samples_per_second": 43.176,
+      "eval_steps_per_second": 5.406,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3135045208375296.0,
+  "total_flos": 6270090416750592.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null