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:fdcd24eb7bbabd8d838ddf8d5d138e8a803ab2b030473e26eeb62ae7ed5ed2e2
+oid sha256:7deb1e142a49efcd53f056dd942e0d558fa4b22ab557c158326b02d1e36f43ba
 size 40036040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2393d84e14e0b608e3c02f84d845738e84fce455ee6d41d403efec849d1d3992
+oid sha256:abcf4a13ddeed657d3357201297b5f215950c47f7c300efabb67aeef85956691
 size 20814996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a85b30d6191fd809940d84dc942a4dd720abe841dfa0fb657ab592db16cfab80
+oid sha256:40e7b2524aeb7e3990808f04ad8fb7c0a9d83353db25ecf1a44802a7e7f7d705
 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,
@@ -49,11 +49,52 @@
       "eval_samples_per_second": 0.116,
       "eval_steps_per_second": 0.058,
       "step": 1
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.0389535129070282,
+      "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": 1.0,
+      "eval_completions/max_length": 256.0,
+      "eval_completions/max_terminated_length": 0.0,
+      "eval_completions/mean_length": 256.0,
+      "eval_completions/mean_terminated_length": 0.0,
+      "eval_completions/min_length": 256.0,
+      "eval_completions/min_terminated_length": 0.0,
+      "eval_kl": 0.00035801943158730865,
+      "eval_loss": 1.4195684343576431e-05,
+      "eval_num_tokens": 1322.0,
+      "eval_reward": -181.89459228515625,
+      "eval_reward_std": 88.72210693359375,
+      "eval_rewards/reward_high_fluency/mean": 0.8197523355484009,
+      "eval_rewards/reward_high_fluency/std": 0.09053098410367966,
+      "eval_rewards/reward_low_severe_toxicity_score/mean": 0.9998976588249207,
+      "eval_rewards/reward_low_severe_toxicity_score/std": 5.608962965197861e-06,
+      "eval_rewards/reward_reasoning_keywords/mean": 1.5,
+      "eval_rewards/reward_reasoning_keywords/std": 1.9148542881011963,
+      "eval_rewards/reward_short_sentences/mean": -23.084821701049805,
+      "eval_rewards/reward_short_sentences/std": 22.075199127197266,
+      "eval_rewards/reward_specific_word_count/mean": -77.75,
+      "eval_rewards/reward_specific_word_count/std": 44.4100227355957,
+      "eval_runtime": 17.3584,
+      "eval_samples_per_second": 0.115,
+      "eval_steps_per_second": 0.058,
+      "step": 2
     }
   ],
   "logging_steps": 1,
   "max_steps": 2,
-  "num_input_tokens_seen": 630,
+  "num_input_tokens_seen": 1322,
   "num_train_epochs": 1,
   "save_steps": 1,
   "stateful_callbacks": {
@@ -63,7 +104,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }