Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e79e7fc32d2580c9d50e60ef68be8b599a8c0568c3a8caa4a14f2d72a29cf6af
+oid sha256:18d8128d3ee97dfc5815897000fb196918d75596b92d9fce4fe4affefcac8f66
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3dd893c207e3d1f2bc028be6b52b91d3d83dc4d2ada4afcc861658c1da027ab
+oid sha256:0ddf3a197c8591f306c043b8e3fe43bd261f16a96d5a694b2a4fb9311a700b0b
 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": 0.0016342094511779927,
+  "epoch": 0.0032684189023559854,
   "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": 27.534,
       "eval_steps_per_second": 13.785,
       "step": 3
+    },
+    {
+      "epoch": 0.00217894593490399,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.0027236824186299877,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.0032684189023559854,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.0032684189023559854,
+      "eval_loss": NaN,
+      "eval_runtime": 28.1627,
+      "eval_samples_per_second": 27.448,
+      "eval_steps_per_second": 13.742,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 740620319588352.0,
+  "total_flos": 1524806540328960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null