Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:069e38c3fc01a054b81543a263bc52b694e989624450854ea20544bd07b1ab16
+oid sha256:fd8faa7b7be9e22aeb9baf1705441609692203178d5a344bc6d55727a0d84b37
 size 67262

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f0301aae68db5017871275fbfdb6928fd6f7537f55caa23bacf0eda6ec47376
+oid sha256:a080d3277fb6ccb5ed989cb90ca2c5dbb10923ca8748d5a82c16ca3dd1e9dbd3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02234156820622986,
+  "epoch": 0.04296455424274973,
   "eval_steps": 10,
-  "global_step": 26,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -66,6 +66,65 @@
       "learning_rate": 6.91341716182545e-05,
       "loss": 0.0,
       "step": 25
+    },
+    {
+      "epoch": 0.02577873254564984,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.02577873254564984,
+      "eval_loss": NaN,
+      "eval_runtime": 2.0793,
+      "eval_samples_per_second": 235.651,
+      "eval_steps_per_second": 117.825,
+      "step": 30
+    },
+    {
+      "epoch": 0.03007518796992481,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.034371643394199784,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.034371643394199784,
+      "eval_loss": NaN,
+      "eval_runtime": 2.1937,
+      "eval_samples_per_second": 223.364,
+      "eval_steps_per_second": 111.682,
+      "step": 40
+    },
+    {
+      "epoch": 0.03866809881847476,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.04296455424274973,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.04296455424274973,
+      "eval_loss": NaN,
+      "eval_runtime": 2.0204,
+      "eval_samples_per_second": 242.523,
+      "eval_steps_per_second": 121.261,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -80,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 686338473984.0,
+  "total_flos": 1320877817856.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null