Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ee7f7e4db091fa1401d5f121303f1d1d80545105915744fdfa445e0c24e594c
+oid sha256:9b9a75f32be63387c28153328a1b0691f9e49ee128269c6ff2216dcfebb420ad
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90ea1f3b22acd0d3c9afd160819677f0b4035afb74fff9b7ea6a0acd9c10b37a
+oid sha256:8ac108aa9eba00358310a4439f789a188dfe5197c585ee0c9b69af254e4ad32c
 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": 0.0037778617302606727,
+  "epoch": 0.007555723460521345,
   "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": 8.925,
       "eval_steps_per_second": 4.463,
       "step": 5
+    },
+    {
+      "epoch": 0.004533434076312807,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.005289006422364941,
+      "grad_norm": NaN,
+      "learning_rate": 7e-05,
+      "loss": 152.26,
+      "step": 7
+    },
+    {
+      "epoch": 0.006044578768417076,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 2.0486,
+      "step": 8
+    },
+    {
+      "epoch": 0.00680015111446921,
+      "grad_norm": NaN,
+      "learning_rate": 9e-05,
+      "loss": 0.0262,
+      "step": 9
+    },
+    {
+      "epoch": 0.007555723460521345,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.285,
+      "step": 10
+    },
+    {
+      "epoch": 0.007555723460521345,
+      "eval_loss": NaN,
+      "eval_runtime": 193.3818,
+      "eval_samples_per_second": 11.532,
+      "eval_steps_per_second": 5.766,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5985653464498176.0,
+  "total_flos": 1.2134181853200384e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null