Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8705f7b20c2fc4425c2cc09780122d9c8066b3058ca0e797030d5fc389c266f4
+oid sha256:23fc48f21c8e92007b0f2ec4049c0456b87a1df4cd2f037e359a4bf001f66ce3
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93ae025875e5e9799a5196ca2599ca81f3c58c08dbc20fc9e7f51b57816fc405
+oid sha256:cd0e9045183916a77f191421cff82618df77003ceaa3909e936c6fdd5d3e7edd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa0fde01e60897f55f4ebaca5a490a1a483a2c53b2ae8e7543860a62c5b3298c
+oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.015247031227092802,
+  "epoch": 0.022870546840639203,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 31.688,
       "eval_steps_per_second": 15.844,
       "step": 26
+    },
+    {
+      "epoch": 0.01583345550505791,
+      "grad_norm": NaN,
+      "learning_rate": 3.083613409639764e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.016419879783023016,
+      "grad_norm": NaN,
+      "learning_rate": 2.8910861626005776e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.017006304060988124,
+      "grad_norm": NaN,
+      "learning_rate": 2.6961477393196126e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.017592728338953232,
+      "grad_norm": NaN,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.01817915261691834,
+      "grad_norm": NaN,
+      "learning_rate": 2.303852260680388e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.018765576894883448,
+      "grad_norm": NaN,
+      "learning_rate": 2.1089138373994223e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.019352001172848556,
+      "grad_norm": NaN,
+      "learning_rate": 1.9163865903602374e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.019938425450813663,
+      "grad_norm": NaN,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.02052484972877877,
+      "grad_norm": NaN,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.02111127400674388,
+      "grad_norm": NaN,
+      "learning_rate": 1.3650237506511331e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.021697698284708987,
+      "grad_norm": NaN,
+      "learning_rate": 1.1937535882101281e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.022284122562674095,
+      "grad_norm": NaN,
+      "learning_rate": 1.0305368692688174e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.022870546840639203,
+      "grad_norm": NaN,
+      "learning_rate": 8.763798791745411e-06,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.022870546840639203,
+      "eval_loss": NaN,
+      "eval_runtime": 22.6084,
+      "eval_samples_per_second": 31.758,
+      "eval_steps_per_second": 15.879,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4776030652858368.0,
+  "total_flos": 7142137581797376.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null