Training in progress, step 336, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1f85361c8b3ee1aefa40068e4fea5744c30caf0c993b42bdf75d606a826c436
+oid sha256:c845921dd5d38c1bc9a1cff2de771649f69d3bc50aeb640737c71d999adb45d0
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aad45149c6b81235cb7dda6b44f33ffe61356d9d41bc3fef8d9ff334d7f6410
+oid sha256:9e6155b2f406e14ae258f21b07526ec14202a94f19efd93172b191f2e0672456
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:318b114b83c26bcba11815378a88e0015bce044b0002c702e0a2627e1a1d1e56
+oid sha256:10affc9ced28dcfaf0d40e3497a97c8e7416bd057324538f99a7e1756fd84408
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.015625622832542752,
+  "epoch": 0.017857854665763145,
   "eval_steps": 42,
-  "global_step": 294,
+  "global_step": 336,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -757,6 +757,112 @@
       "eval_samples_per_second": 13.383,
       "eval_steps_per_second": 1.673,
       "step": 294
+    },
+    {
+      "epoch": 0.015785067963487064,
+      "grad_norm": NaN,
+      "learning_rate": 3.6698157721666246e-05,
+      "loss": 0.0,
+      "step": 297
+    },
+    {
+      "epoch": 0.01594451309443138,
+      "grad_norm": NaN,
+      "learning_rate": 3.5773620668448384e-05,
+      "loss": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.016103958225375692,
+      "grad_norm": NaN,
+      "learning_rate": 3.48543465876014e-05,
+      "loss": 0.0,
+      "step": 303
+    },
+    {
+      "epoch": 0.016263403356320007,
+      "grad_norm": NaN,
+      "learning_rate": 3.3940675559617724e-05,
+      "loss": 0.0,
+      "step": 306
+    },
+    {
+      "epoch": 0.01642284848726432,
+      "grad_norm": NaN,
+      "learning_rate": 3.303294559217063e-05,
+      "loss": 0.0,
+      "step": 309
+    },
+    {
+      "epoch": 0.016582293618208635,
+      "grad_norm": NaN,
+      "learning_rate": 3.213149249506997e-05,
+      "loss": 0.0,
+      "step": 312
+    },
+    {
+      "epoch": 0.016741738749152947,
+      "grad_norm": NaN,
+      "learning_rate": 3.12366497560313e-05,
+      "loss": 0.0,
+      "step": 315
+    },
+    {
+      "epoch": 0.016901183880097263,
+      "grad_norm": NaN,
+      "learning_rate": 3.0348748417303823e-05,
+      "loss": 0.0,
+      "step": 318
+    },
+    {
+      "epoch": 0.017060629011041575,
+      "grad_norm": NaN,
+      "learning_rate": 2.9468116953203107e-05,
+      "loss": 0.0,
+      "step": 321
+    },
+    {
+      "epoch": 0.01722007414198589,
+      "grad_norm": NaN,
+      "learning_rate": 2.8595081148593738e-05,
+      "loss": 0.0,
+      "step": 324
+    },
+    {
+      "epoch": 0.017379519272930202,
+      "grad_norm": NaN,
+      "learning_rate": 2.772996397836704e-05,
+      "loss": 0.0,
+      "step": 327
+    },
+    {
+      "epoch": 0.017538964403874518,
+      "grad_norm": NaN,
+      "learning_rate": 2.687308548795825e-05,
+      "loss": 0.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.01769840953481883,
+      "grad_norm": NaN,
+      "learning_rate": 2.6024762674947313e-05,
+      "loss": 0.0,
+      "step": 333
+    },
+    {
+      "epoch": 0.017857854665763145,
+      "grad_norm": NaN,
+      "learning_rate": 2.5185309371787513e-05,
+      "loss": 0.0,
+      "step": 336
+    },
+    {
+      "epoch": 0.017857854665763145,
+      "eval_loss": NaN,
+      "eval_runtime": 2368.7091,
+      "eval_samples_per_second": 13.378,
+      "eval_steps_per_second": 1.673,
+      "step": 336
     }
   ],
   "logging_steps": 3,
@@ -776,7 +882,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.495370464662651e+17,
+  "total_flos": 5.13648873562964e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null