Training in progress, step 150, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61fb5b78cc5a167482399cc97c87bcf903f86a4c8bd69daadaebb13589e5a57b
+oid sha256:69e0cd5296079ffc15a035b3eca454f686d69c252d72318c2fd10c1e9c5486d2
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0fa753fb951b0fd819d629c13f53f36a173271d4758904221c7092e57242a05
+oid sha256:a8842814fcbb5bf82c20ef3e8fe248730f63f6eea210e672a9d5639a70f212f0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
+oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009708973518774727,
+  "epoch": 0.014563460278162091,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 28.146,
       "eval_steps_per_second": 14.076,
       "step": 100
+    },
+    {
+      "epoch": 0.0106798708706522,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 6.0712,
+      "step": 110
+    },
+    {
+      "epoch": 0.011650768222529672,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.217,
+      "step": 120
+    },
+    {
+      "epoch": 0.012621665574407146,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 2.4564,
+      "step": 130
+    },
+    {
+      "epoch": 0.01359256292628462,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 4.3601,
+      "step": 140
+    },
+    {
+      "epoch": 0.014563460278162091,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 2.635,
+      "step": 150
+    },
+    {
+      "epoch": 0.014563460278162091,
+      "eval_loss": NaN,
+      "eval_runtime": 154.1373,
+      "eval_samples_per_second": 28.137,
+      "eval_steps_per_second": 14.072,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1163499820417024e+16,
+  "total_flos": 3.150425749664563e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null