Training in progress, epoch 1, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46c697a9b015420a4013c5b68adb66f26f8468702284e951c2f69f52eb842023
+oid sha256:b83cfd40c70314fce5903b238cebc3405e46b61fcfcc917de27a01a36c9957fa
 size 557116312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17c36f6e33823fb847e839ad1db74a553a1c63d5426ff26051bcfea745dae252
+oid sha256:e28573f5b7a0557a8eb20a897636afe29a35ef448df6b4d979112ee58fe97537
 size 1113991930

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef2b170a520baa1ce18377bdacbbdccab7978596a4a772af3bdbdf4cfda617a7
+oid sha256:59624509e89bbc9b94c591ed4735982e33caa7e6875690c4ff16d1a97717d87c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be41d27c52015159c12ea1a39d342a8acabee4a3e8b9b9a41f77607cbb01aef6
+oid sha256:696ca044b381ad728856a952b16ab56061698c9ae78b0db6fa4cd76b3bd2630e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,82 +1,50 @@
 {
-  "best_metric": 25.1709,
+  "best_metric": 25.4939,
   "best_model_checkpoint": "my-model/checkpoint-1528",
-  "epoch": 2.0,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 3056,
+  "global_step": 1528,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.32722513089005234,
-      "grad_norm": 0.9616150856018066,
-      "learning_rate": 4.454624781849913e-05,
-      "loss": 0.0158,
+      "grad_norm": 1.691941261291504,
+      "learning_rate": 4.181937172774869e-05,
+      "loss": 0.0156,
       "step": 500
     },
     {
       "epoch": 0.6544502617801047,
-      "grad_norm": 2.0808584690093994,
-      "learning_rate": 3.909249563699826e-05,
-      "loss": 0.0223,
+      "grad_norm": 2.3052828311920166,
+      "learning_rate": 3.3638743455497386e-05,
+      "loss": 0.0188,
       "step": 1000
     },
     {
       "epoch": 0.981675392670157,
-      "grad_norm": 1.145504117012024,
-      "learning_rate": 3.3638743455497386e-05,
-      "loss": 0.0271,
+      "grad_norm": 1.2767335176467896,
+      "learning_rate": 2.545811518324607e-05,
+      "loss": 0.019,
       "step": 1500
     },
     {
       "epoch": 1.0,
-      "eval_loss": 5.483295917510986,
-      "eval_rouge1": 25.1709,
-      "eval_rouge2": 10.0024,
-      "eval_rougeL": 21.9926,
-      "eval_runtime": 372.8877,
-      "eval_samples_per_second": 5.886,
-      "eval_steps_per_second": 0.59,
+      "eval_loss": 5.557580471038818,
+      "eval_rouge1": 25.4939,
+      "eval_rouge2": 10.2057,
+      "eval_rougeL": 22.1893,
+      "eval_runtime": 394.3343,
+      "eval_samples_per_second": 5.566,
+      "eval_steps_per_second": 0.558,
       "step": 1528
-    },
-    {
-      "epoch": 1.3089005235602094,
-      "grad_norm": 3.2998411655426025,
-      "learning_rate": 2.8184991273996508e-05,
-      "loss": 0.0416,
-      "step": 2000
-    },
-    {
-      "epoch": 1.6361256544502618,
-      "grad_norm": 1.5071967840194702,
-      "learning_rate": 2.273123909249564e-05,
-      "loss": 0.0513,
-      "step": 2500
-    },
-    {
-      "epoch": 1.9633507853403143,
-      "grad_norm": 4.118706226348877,
-      "learning_rate": 1.7277486910994763e-05,
-      "loss": 0.0687,
-      "step": 3000
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 5.419973373413086,
-      "eval_rouge1": 24.9529,
-      "eval_rouge2": 9.9221,
-      "eval_rougeL": 21.6944,
-      "eval_runtime": 386.7275,
-      "eval_samples_per_second": 5.676,
-      "eval_steps_per_second": 0.569,
-      "step": 3056
     }
   ],
   "logging_steps": 500,
-  "max_steps": 4584,
+  "max_steps": 3056,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -90,7 +58,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4662889498529792e+16,
+  "total_flos": 7327420304523264.0,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9454715524d57fa2a7a3e1d17cb27d9ba1a09c66d019637bdd23107b92238a57
+oid sha256:ab242239cdb15c114c4811b4337d536862b845b65e398ba83e56979928aa7eb2
 size 6968