Training in progress, step 100, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e22fc3a12d2efbb847641612501e4278552076c91de3a71ee5f75fba516eb3c1
+oid sha256:3ea7aee0acdcae3efed24176f2c4c8ced4e25f1c8859da868dca484ac61418e5
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d67cef9c988719cba8883d1990d1b0cdb6b0ce358c09847ec80740d69ae7a53d
+oid sha256:8a7f1807a79f764cdbf1638aa0e0db1154794499b1015a5180c25c186b8d6d94
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8148b27980adb9b0bdd5c04049e531bfefcc05c06612ee72169cfb9b9fd7ee7
+oid sha256:0fd8212ec5ec3406d74a7f927b717dd30ea8a06115ee6582e14976f7b84b4b58
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.13449899125756556,
+  "epoch": 0.26899798251513113,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 20.862,
       "eval_steps_per_second": 10.498,
       "step": 50
+    },
+    {
+      "epoch": 0.16139878950907868,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016324453755953773,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.1882985877605918,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.21519838601210492,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013546048870425356,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.242098184263618,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012000256937760445,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.26899798251513113,
+      "grad_norm": NaN,
+      "learning_rate": 0.00010402659401094152,
+      "loss": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.26899798251513113,
+      "eval_loss": NaN,
+      "eval_runtime": 7.5278,
+      "eval_samples_per_second": 20.856,
+      "eval_steps_per_second": 10.494,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.586645434368e+16,
+  "total_flos": 3.173290868736e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null