Training in progress, epoch 6, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a9ad4c7f45b1d7df8dfc104dd086ff90207c112c2d4e0353522c2262ea931b1
+oid sha256:834e5ea995fe8ae27d6cf4e789cac2d81d453799e84d43e62c4dc4eab3e479ee
 size 1625422896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbf9a7a18d7146d027b6ed81274b5cc55d4d394269b589486d9e2f81279b196e
+oid sha256:772d73a38fb4660e040157b6af8aa2d51d2b4e3306c7a0e149fc8d2a414416b2
 size 3250751759

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9fd4b737be4b245498b329a1152267380d7568cb3b3af8cc3ced02ef2c48ac4
+oid sha256:1e53d97d145daeb7f4024f8b61a8557cf89848b778d276c461f2b8bd31c089ec
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ec99de839621be0598a6a2c36a34e5fa9d00fc674f048c9568befe6365b6ffd
+oid sha256:f3bde17d147c33d13c6a44a01a7e071b043b4c31ca2b85ecaa3a4136a6b27de3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.989690721649485,
+  "epoch": 6.989690721649485,
   "eval_steps": 500,
-  "global_step": 378,
+  "global_step": 441,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -127,6 +127,26 @@
       "eval_samples_per_second": 0.348,
       "eval_steps_per_second": 0.087,
       "step": 378
+    },
+    {
+      "epoch": 6.989690721649485,
+      "grad_norm": 0.8424471020698547,
+      "learning_rate": 6.5000000000000004e-06,
+      "loss": 2.3149,
+      "step": 441
+    },
+    {
+      "epoch": 6.989690721649485,
+      "eval_gen_len": 254.68467,
+      "eval_loss": 2.3630220890045166,
+      "eval_rouge1": 0.388393,
+      "eval_rouge2": 0.083801,
+      "eval_rougeL": 0.187039,
+      "eval_rougeLsum": 0.361264,
+      "eval_runtime": 3555.8921,
+      "eval_samples_per_second": 0.354,
+      "eval_steps_per_second": 0.089,
+      "step": 441
     }
   ],
   "logging_steps": 500,
@@ -134,7 +154,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 1.0590640190521344e+17,
+  "total_flos": 1.2355746888941568e+17,
   "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 sha256:2416be29a9ae31ec464493ebce88155572267b0992da3587f0275166bb7e6f09
+oid sha256:cf6b5f7dff1de33af8ceebc6411598f61c4fe76ab61644fd8716ce497d107aa5
 size 5112