Training in progress, epoch 4, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60afd84760802444ae58550d1896fc22db404e1b9ac0fead40f9c30c6e047045
+oid sha256:a8201f18535a29f04f89563cbe35511097be9afba3b01a1e701eb8781948a7e3
 size 1625422896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4c7f41b4b79b88ffeb95e5eeb7ba629814254d8304f6658c89cbc116aa6db8f
+oid sha256:1abcae7ab0e3b9ac6edbd28550a312b42a9c47fdf907f89ba856c5bf3237c056
 size 3250751759

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de1bfc2d268cf7923378b9b2e0fe99c311d8b932bea99f486a350f50ffd9e101
+oid sha256:df39f38db37f6701456fe0a4817ff33122927ab7938b1eea653c5a371678f4e6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:426dcb52d1996a4c433b718765d7d5084e38f73a5d455b904f91da402171e701
+oid sha256:83abdcd16b2b9b2191fd1f05501acfc5e3cc7f2d27d51fac1f0aca438433a1b0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.9896907216494846,
+  "epoch": 4.989690721649485,
   "eval_steps": 500,
-  "global_step": 252,
+  "global_step": 315,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -87,6 +87,26 @@
       "eval_samples_per_second": 0.36,
       "eval_steps_per_second": 0.09,
       "step": 252
+    },
+    {
+      "epoch": 4.989690721649485,
+      "grad_norm": 0.8451509475708008,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 2.3836,
+      "step": 315
+    },
+    {
+      "epoch": 4.989690721649485,
+      "eval_gen_len": 254.285147,
+      "eval_loss": 2.3810665607452393,
+      "eval_rouge1": 0.382543,
+      "eval_rouge2": 0.079173,
+      "eval_rougeL": 0.183712,
+      "eval_rougeLsum": 0.355298,
+      "eval_runtime": 3613.6748,
+      "eval_samples_per_second": 0.348,
+      "eval_steps_per_second": 0.087,
+      "step": 315
     }
   ],
   "logging_steps": 500,
@@ -94,7 +114,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 7.060426793680896e+16,
+  "total_flos": 8.82553349210112e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:118bb6421b373e0e03ecd8aab7a5860a2b18c80d88abafa457126607b17fd56f
+oid sha256:4f1906cfa0ad9e14e9f7f606dee91b794900b0ec7b1452c25901d0c904a02a7b
 size 5112