Training in progress, step 2, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bfc1773a3c26bdc718e0e6aa005fb219e8ffa174f1ba87c39fc0100fab8852b
+oid sha256:b892fa86457b9cdfeb2a1ff30b4719803854c3a3e1b9bc8d48638aa70e5c3ea1
 size 12655792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9782e339f31665f3d37f6db0bb9a8b028184660aa43a8c7c781c4ccf7487e7b0
+oid sha256:ccac18f5478d324c379aef03cdea62bf0338a300406cdfe1b4cb66000013a6ca
 size 7005964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c65d6fc438bdde662c4aeccd9eae6f546227f7a9f594daf6230a9e77181f3597
+oid sha256:80daa1085c1bb74fa1778065e9fd3af9b35bd5ed72a9ec43d90f9b358d1b5b40
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:764cf599d0b83c5d302be0978d09e435a466a8511dc1f7e86d5ee3704818d46f
+oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03333333333333333,
+  "epoch": 0.06666666666666667,
   "eval_steps": 1,
-  "global_step": 1,
+  "global_step": 2,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -43,11 +43,46 @@
       "eval_samples_per_second": 0.62,
       "eval_steps_per_second": 0.31,
       "step": 1
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.1393648087978363,
+      "learning_rate": 2e-05,
+      "loss": 0.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "eval_clip_ratio/high_max": 0.0,
+      "eval_clip_ratio/high_mean": 0.0,
+      "eval_clip_ratio/low_mean": 0.0,
+      "eval_clip_ratio/low_min": 0.0,
+      "eval_clip_ratio/region_mean": 0.0,
+      "eval_completions/clipped_ratio": 0.5,
+      "eval_completions/max_length": 256.0,
+      "eval_completions/max_terminated_length": 114.0,
+      "eval_completions/mean_length": 185.0,
+      "eval_completions/mean_terminated_length": 114.0,
+      "eval_completions/min_length": 114.0,
+      "eval_completions/min_terminated_length": 114.0,
+      "eval_kl": 0.0004723518795799464,
+      "eval_loss": 0.447740375995636,
+      "eval_num_tokens": 943.0,
+      "eval_reward": -865.9603271484375,
+      "eval_reward_std": 681.6474609375,
+      "eval_rewards/reward_long_words/mean": 4.207789421081543,
+      "eval_rewards/reward_long_words/std": 2.8054802417755127,
+      "eval_rewards/reward_specific_word_count/mean": -92.5,
+      "eval_rewards/reward_specific_word_count/std": 59.66852951049805,
+      "eval_runtime": 12.6295,
+      "eval_samples_per_second": 0.158,
+      "eval_steps_per_second": 0.079,
+      "step": 2
     }
   ],
   "logging_steps": 1,
   "max_steps": 2,
-  "num_input_tokens_seen": 345,
+  "num_input_tokens_seen": 943,
   "num_train_epochs": 1,
   "save_steps": 1,
   "stateful_callbacks": {
@@ -57,7 +92,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }