Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b08cbbdd2c01905b9bbb35efe01a64d8d1971e601658701a22ba01fb7d3d46b
+oid sha256:1fe030221ae30a0c9026ea289035be504b1f53fcf486249a5184138b9d3e35ea
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54a660fe1685e8a6b7a3af3fc232b2540a63f4d3847dc6daad940db92f4e5b7e
+oid sha256:bbba3e37f3da5eebd20241eda5b6317a6fa8037aef8c40511f6d82de78527891
 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": 0.027520508070918232,
+  "epoch": 0.04128076210637735,
   "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": 63.465,
       "eval_steps_per_second": 31.733,
       "step": 26
+    },
+    {
+      "epoch": 0.028578989150568935,
+      "grad_norm": NaN,
+      "learning_rate": 3.083613409639764e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.029637470230219634,
+      "grad_norm": NaN,
+      "learning_rate": 2.8910861626005776e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.030695951309870337,
+      "grad_norm": NaN,
+      "learning_rate": 2.6961477393196126e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.03175443238952104,
+      "grad_norm": NaN,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.032812913469171735,
+      "grad_norm": NaN,
+      "learning_rate": 2.303852260680388e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.03387139454882244,
+      "grad_norm": NaN,
+      "learning_rate": 2.1089138373994223e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.03492987562847314,
+      "grad_norm": NaN,
+      "learning_rate": 1.9163865903602374e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.03598835670812384,
+      "grad_norm": NaN,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.037046837787774546,
+      "grad_norm": NaN,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.03810531886742524,
+      "grad_norm": NaN,
+      "learning_rate": 1.3650237506511331e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.039163799947075945,
+      "grad_norm": NaN,
+      "learning_rate": 1.1937535882101281e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.04022228102672665,
+      "grad_norm": NaN,
+      "learning_rate": 1.0305368692688174e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.04128076210637735,
+      "grad_norm": NaN,
+      "learning_rate": 8.763798791745411e-06,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.04128076210637735,
+      "eval_loss": NaN,
+      "eval_runtime": 6.2404,
+      "eval_samples_per_second": 63.778,
+      "eval_steps_per_second": 31.889,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 231499225890816.0,
+  "total_flos": 347248838836224.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null