Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:090c731607352eeae2dc4e4e6a3233c5bacb8400419b2f7a57cd84463f204ad5
+oid sha256:e2440a147239f2274a6c9b5df044575d1758dc56514dd0c726b571620ac755c1
 size 134218

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1157d27dce2dcecce45248d3e13fbeed0132d6326173a8b19bd68a0fc44b2915
+oid sha256:c900d4c6853d677a7868b2838751ed164390e83255a80643445dc284e68bad62
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fc9c0ec571f76cf9b6d1229601c5173899cd18104e487c5627f5f4c56c6e8a
+oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00638141731278517,
+  "epoch": 0.01276283462557034,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 242.108,
       "eval_steps_per_second": 121.054,
       "step": 25
+    },
+    {
+      "epoch": 0.006636674005296576,
+      "grad_norm": NaN,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.006891930697807983,
+      "grad_norm": NaN,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.00714718739031939,
+      "grad_norm": NaN,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.007402444082830797,
+      "grad_norm": NaN,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.0076577007753422036,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.00791295746785361,
+      "grad_norm": NaN,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.008168214160365016,
+      "grad_norm": NaN,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.008423470852876425,
+      "grad_norm": NaN,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.008678727545387831,
+      "grad_norm": NaN,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.008933984237899237,
+      "grad_norm": NaN,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.009189240930410644,
+      "grad_norm": NaN,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.00944449762292205,
+      "grad_norm": NaN,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.009699754315433459,
+      "grad_norm": NaN,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.009955011007944865,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.010210267700456271,
+      "grad_norm": NaN,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.010465524392967678,
+      "grad_norm": NaN,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.010720781085479084,
+      "grad_norm": NaN,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.010976037777990492,
+      "grad_norm": NaN,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.011231294470501899,
+      "grad_norm": NaN,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.011486551163013305,
+      "grad_norm": NaN,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.011741807855524712,
+      "grad_norm": NaN,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.011997064548036118,
+      "grad_norm": NaN,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.012252321240547526,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.012507577933058933,
+      "grad_norm": NaN,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.01276283462557034,
+      "grad_norm": NaN,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.01276283462557034,
+      "eval_loss": NaN,
+      "eval_runtime": 13.6377,
+      "eval_samples_per_second": 241.976,
+      "eval_steps_per_second": 120.988,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5244361113600.0,
+  "total_flos": 10411219353600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null