Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a4195a33f6973f6dad4816fac0acc39d254b0c10d6c8f19eeaf14520c93ec04
+oid sha256:ae4cbc794931e2dbb866c3999ae2a03c34864f90a68fc2afcba1147394e3f437
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff226c15e19b8085e09f0025aa31f4d46c591e213735b264a5e28d7f9728a70c
+oid sha256:6011dbc1beaf916a24aa0692a7ad3787fe62f4d3127d9859b27643438838594d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02476780185758514,
+  "epoch": 0.04953560371517028,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 32.025,
       "eval_steps_per_second": 16.013,
       "step": 5
+    },
+    {
+      "epoch": 0.029721362229102165,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.0346749226006192,
+      "grad_norm": NaN,
+      "learning_rate": 7e-05,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.039628482972136225,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.04458204334365325,
+      "grad_norm": NaN,
+      "learning_rate": 9e-05,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.04953560371517028,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.04953560371517028,
+      "eval_loss": NaN,
+      "eval_runtime": 10.499,
+      "eval_samples_per_second": 32.384,
+      "eval_steps_per_second": 16.192,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3559316143472640.0,
+  "total_flos": 7210485606776832.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null