Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24f47ddd4884e6a4f3bac407a7bb5c7f96019f61a010b4c239e1d97e79684b9c
+oid sha256:58127ec95c47906630700b67ebefd82002b7f15d052f046d10bd905bba926c37
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8580306d32b005c0733c680a2aa90baffc7bb3fab9f44ba259f139790c0142d8
+oid sha256:41f0feddd7998b877f7ccc370756fc2edae64edd6baec5679a7765fc8dac5cdc
 size 14244

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": 0.003459210147016431,
+  "epoch": 0.006918420294032862,
   "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": 6.662,
       "eval_steps_per_second": 3.331,
       "step": 3
+    },
+    {
+      "epoch": 0.004612280196021909,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.005765350245027385,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.006918420294032862,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.006918420294032862,
+      "eval_loss": NaN,
+      "eval_runtime": 54.9845,
+      "eval_samples_per_second": 6.656,
+      "eval_steps_per_second": 3.328,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 216286290247680.0,
+  "total_flos": 432572580495360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null