Training in progress, epoch 2, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0321845aa554c15389dd24dff69e92c7373fc5b04cb68327a41cdc98bbcd31ba
+oid sha256:46c697a9b015420a4013c5b68adb66f26f8468702284e951c2f69f52eb842023
 size 557116312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62afe7d04b548ec8eec3d1689d7d8c3e8d969ad62a70b280216e862ba19c8547
+oid sha256:17c36f6e33823fb847e839ad1db74a553a1c63d5426ff26051bcfea745dae252
 size 1113991930

last-checkpoint/rng_state.pth

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

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ac9643ef164647dd74d17c68b79347a9f51627588cd7ec3dd1a18bf83f7e68f
+oid sha256:be41d27c52015159c12ea1a39d342a8acabee4a3e8b9b9a41f77607cbb01aef6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 25.1709,
   "best_model_checkpoint": "my-model/checkpoint-1528",
-  "epoch": 1.0,
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 1528,
+  "global_step": 3056,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -39,6 +39,38 @@
       "eval_samples_per_second": 5.886,
       "eval_steps_per_second": 0.59,
       "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,
@@ -58,7 +90,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7327420304523264.0,
+  "total_flos": 1.4662889498529792e+16,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null