Training in progress, step 7, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6c63892f23bc87e96b2a7607a15382b3d8853c2de9adaa33a1fba1de5869ab5
+oid sha256:05fc18f0cbec6af1db3db6281a0c6e5f835ffb493f44b987eb58da9fddc23abf
 size 8749702

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e39beece3a04ad324e9d493363868b1a4ca42fb2d9c9e3591b853d4823466d89
+oid sha256:ef66f33e0e8651beb12025593fb655908904f24fc54b6e71ead32c12c3d8f782
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e086a14b4bc4515be249820c5a7e01483f6ee3cb4269224cebb29a3b0b15a6d
+oid sha256:7e56cf43ea420ffb89f8af2e790fe4087ec74a9039af94c27230aaa84a739018
 size 2080

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013579461065138977,
+  "epoch": 0.02376405686399321,
   "eval_steps": 1,
-  "global_step": 4,
+  "global_step": 7,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -67,6 +67,51 @@
       "eval_samples_per_second": 16.076,
       "eval_steps_per_second": 16.076,
       "step": 4
+    },
+    {
+      "epoch": 0.016974326331423723,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019999999494757503,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.016974326331423723,
+      "eval_loss": NaN,
+      "eval_runtime": 16.1922,
+      "eval_samples_per_second": 15.378,
+      "eval_steps_per_second": 15.378,
+      "step": 5
+    },
+    {
+      "epoch": 0.020369191597708464,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090168305207044,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.020369191597708464,
+      "eval_loss": NaN,
+      "eval_runtime": 16.0044,
+      "eval_samples_per_second": 15.558,
+      "eval_steps_per_second": 15.558,
+      "step": 6
+    },
+    {
+      "epoch": 0.02376405686399321,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001309016952291131,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.02376405686399321,
+      "eval_loss": NaN,
+      "eval_runtime": 14.7177,
+      "eval_samples_per_second": 16.918,
+      "eval_steps_per_second": 16.918,
+      "step": 7
     }
   ],
   "logging_steps": 1,
@@ -86,7 +131,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 253109804728320.0,
+  "total_flos": 442942158274560.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null