Training in progress, step 36, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd1eacc253ed658fec54ab602ab00e6d3857fdae9e10c456f13576ce049a790e
+oid sha256:47a038fef243758fba89c209702626b9bd41ab89a37c758066075ffee412222d
 size 275817586

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:696c9813570a7d5a6018e9b99e6478844a73b48e7241f11f1b9df2a6a99d8955
+oid sha256:5498cb3f23923a81ddbe38e7a904596386f3b3410458e28d1669866c5b026dac
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2cf2c4048d6740354979367cfe53d0c735909b56d447ba3e528d55c38895176
+oid sha256:24f70974ebe6e16031ce63527ce3fea95f8e56e83073513783f6d8a14f9aa0e8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0074142724745134385,
+  "epoch": 0.014828544949026877,
   "eval_steps": 5,
-  "global_step": 18,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -81,6 +81,80 @@
       "learning_rate": 0.0002,
       "loss": 0.0,
       "step": 18
+    },
+    {
+      "epoch": 0.008238080527237153,
+      "eval_loss": NaN,
+      "eval_runtime": 317.6442,
+      "eval_samples_per_second": 3.221,
+      "eval_steps_per_second": 1.612,
+      "step": 20
+    },
+    {
+      "epoch": 0.008649984553599012,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001879473751206489,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.009885696632684585,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015469481581224272,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.010297600659046443,
+      "eval_loss": NaN,
+      "eval_runtime": 318.0146,
+      "eval_samples_per_second": 3.217,
+      "eval_steps_per_second": 1.61,
+      "step": 25
+    },
+    {
+      "epoch": 0.011121408711770158,
+      "grad_norm": NaN,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.01235712079085573,
+      "grad_norm": NaN,
+      "learning_rate": 5.983045753470308e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.01235712079085573,
+      "eval_loss": NaN,
+      "eval_runtime": 317.4705,
+      "eval_samples_per_second": 3.222,
+      "eval_steps_per_second": 1.613,
+      "step": 30
+    },
+    {
+      "epoch": 0.013592832869941304,
+      "grad_norm": NaN,
+      "learning_rate": 2.1085949060360654e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.014416640922665019,
+      "eval_loss": NaN,
+      "eval_runtime": 317.6364,
+      "eval_samples_per_second": 3.221,
+      "eval_steps_per_second": 1.612,
+      "step": 35
+    },
+    {
+      "epoch": 0.014828544949026877,
+      "grad_norm": NaN,
+      "learning_rate": 1.3638696597277679e-06,
+      "loss": 0.0,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -100,7 +174,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2753894069239808e+16,
+  "total_flos": 2.5507788138479616e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null