Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bd019c8bd3883c3a423047c7e840d7c93d1e7c6fe8b4d17c8b6e05a7f762913
+oid sha256:2188487222c2aae89f0d513823f01a5f2fbcc832768fdc62b9923739e0d96b88
 size 50721146

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6503571f36e48092a85f3d009d0ef21ae2d8f64c4aaf71c6fa67a336fe827cf
+oid sha256:6c993fb43bf3405764c81336990c5a53605066dec0f82e5a011d6eb7397b80ef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1e2ed9259304616a8ecebc61c5d000777b2978635f7a705b8d7081c480ce0bde
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00030844205915918696,
+  "epoch": 0.0006168841183183739,
   "eval_steps": 2,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -125,6 +125,116 @@
       "eval_samples_per_second": 29.209,
       "eval_steps_per_second": 14.605,
       "step": 10
+    },
+    {
+      "epoch": 0.00033928626507510564,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.0003701304709910243,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0003701304709910243,
+      "eval_loss": NaN,
+      "eval_runtime": 467.4243,
+      "eval_samples_per_second": 29.205,
+      "eval_steps_per_second": 14.603,
+      "step": 12
+    },
+    {
+      "epoch": 0.00040097467690694305,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.00043181888282286173,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.00043181888282286173,
+      "eval_loss": NaN,
+      "eval_runtime": 467.5965,
+      "eval_samples_per_second": 29.194,
+      "eval_steps_per_second": 14.598,
+      "step": 14
+    },
+    {
+      "epoch": 0.0004626630887387804,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0004935072946546991,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.0004935072946546991,
+      "eval_loss": NaN,
+      "eval_runtime": 467.5922,
+      "eval_samples_per_second": 29.194,
+      "eval_steps_per_second": 14.598,
+      "step": 16
+    },
+    {
+      "epoch": 0.0005243515005706178,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.0005551957064865365,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.0005551957064865365,
+      "eval_loss": NaN,
+      "eval_runtime": 467.1377,
+      "eval_samples_per_second": 29.223,
+      "eval_steps_per_second": 14.612,
+      "step": 18
+    },
+    {
+      "epoch": 0.0005860399124024552,
+      "grad_norm": NaN,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.0006168841183183739,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.0006168841183183739,
+      "eval_loss": NaN,
+      "eval_runtime": 467.1363,
+      "eval_samples_per_second": 29.223,
+      "eval_steps_per_second": 14.612,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -139,12 +249,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1023167913000960.0,
+  "total_flos": 2046335826001920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null