Training in progress, step 294, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5a7ed7529369a516560ebe1c26cfdba51e8269d23e3b7413f58c09ab2069175
-size 341314196
+oid sha256:e1f85361c8b3ee1aefa40068e4fea5744c30caf0c993b42bdf75d606a826c436
+size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31fef74ecc274c1e583f98d996eb610b459d5a80f6a2f818f0df2c8347af678c
+oid sha256:2aad45149c6b81235cb7dda6b44f33ffe61356d9d41bc3fef8d9ff334d7f6410
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee19ddad9c4c375a1de2d74fb4c1cf5e15d36c1ed47a2cb80f7cb0fbacb3b29e
+oid sha256:318b114b83c26bcba11815378a88e0015bce044b0002c702e0a2627e1a1d1e56
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013393390999322359,
+  "epoch": 0.015625622832542752,
   "eval_steps": 42,
-  "global_step": 252,
+  "global_step": 294,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -651,6 +651,112 @@
       "eval_samples_per_second": 13.377,
       "eval_steps_per_second": 1.672,
       "step": 252
+    },
+    {
+      "epoch": 0.013552836130266673,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 255
+    },
+    {
+      "epoch": 0.013712281261210985,
+      "grad_norm": NaN,
+      "learning_rate": 4.903834726061565e-05,
+      "loss": 0.0,
+      "step": 258
+    },
+    {
+      "epoch": 0.013871726392155299,
+      "grad_norm": NaN,
+      "learning_rate": 4.807705027948008e-05,
+      "loss": 0.0,
+      "step": 261
+    },
+    {
+      "epoch": 0.014031171523099613,
+      "grad_norm": NaN,
+      "learning_rate": 4.711646468323129e-05,
+      "loss": 0.0,
+      "step": 264
+    },
+    {
+      "epoch": 0.014190616654043926,
+      "grad_norm": NaN,
+      "learning_rate": 4.6156945835334184e-05,
+      "loss": 0.0,
+      "step": 267
+    },
+    {
+      "epoch": 0.01435006178498824,
+      "grad_norm": NaN,
+      "learning_rate": 4.5198848704615914e-05,
+      "loss": 0.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.014509506915932554,
+      "grad_norm": NaN,
+      "learning_rate": 4.424252773394704e-05,
+      "loss": 0.0,
+      "step": 273
+    },
+    {
+      "epoch": 0.014668952046876868,
+      "grad_norm": NaN,
+      "learning_rate": 4.328833670911724e-05,
+      "loss": 0.0,
+      "step": 276
+    },
+    {
+      "epoch": 0.014828397177821181,
+      "grad_norm": NaN,
+      "learning_rate": 4.23366286279542e-05,
+      "loss": 0.0,
+      "step": 279
+    },
+    {
+      "epoch": 0.014987842308765495,
+      "grad_norm": NaN,
+      "learning_rate": 4.138775556973406e-05,
+      "loss": 0.0,
+      "step": 282
+    },
+    {
+      "epoch": 0.015147287439709809,
+      "grad_norm": NaN,
+      "learning_rate": 4.04420685649314e-05,
+      "loss": 0.0,
+      "step": 285
+    },
+    {
+      "epoch": 0.015306732570654123,
+      "grad_norm": NaN,
+      "learning_rate": 3.9499917465357534e-05,
+      "loss": 0.0,
+      "step": 288
+    },
+    {
+      "epoch": 0.015466177701598437,
+      "grad_norm": NaN,
+      "learning_rate": 3.856165081473474e-05,
+      "loss": 0.0,
+      "step": 291
+    },
+    {
+      "epoch": 0.015625622832542752,
+      "grad_norm": NaN,
+      "learning_rate": 3.762761571975429e-05,
+      "loss": 0.0,
+      "step": 294
+    },
+    {
+      "epoch": 0.015625622832542752,
+      "eval_loss": NaN,
+      "eval_runtime": 2367.8949,
+      "eval_samples_per_second": 13.383,
+      "eval_steps_per_second": 1.673,
+      "step": 294
     }
   ],
   "logging_steps": 3,
@@ -670,7 +776,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.8391670579082035e+17,
+  "total_flos": 4.495370464662651e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null