Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03bb90a3c3613e9c42f79f936d3541d890f41c55ef9b10c2b02e0d989c124ad2
+oid sha256:300a59a55c6991643fda02fe701f804e7f91f4dc9027e5bfe22fdaa1790f95a2
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:747d3259b179bd8b916514c25e65c0d98197b14bf3e1b4faabd37d82bece51b7
+oid sha256:2f30e104c7935b532f8e1d94f8f08b4b33a4fbcbda415e4e900b851d33caf842
 size 20632762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff1a5a76862bbee56a9275ee6a5621dff6f0928cd044fcf7d46b0f5941256ac
+oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
+oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02616516762060507,
+  "epoch": 0.05233033524121014,
   "eval_steps": 2,
-  "global_step": 2,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 96.644,
       "eval_steps_per_second": 48.696,
       "step": 2
+    },
+    {
+      "epoch": 0.039247751430907606,
+      "grad_norm": 10.42636775970459,
+      "learning_rate": 3e-05,
+      "loss": 6.2818,
+      "step": 3
+    },
+    {
+      "epoch": 0.05233033524121014,
+      "grad_norm": 12.024919509887695,
+      "learning_rate": 4e-05,
+      "loss": 6.8509,
+      "step": 4
+    },
+    {
+      "epoch": 0.05233033524121014,
+      "eval_loss": 7.859395980834961,
+      "eval_runtime": 1.3481,
+      "eval_samples_per_second": 95.692,
+      "eval_steps_per_second": 48.217,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 391582234705920.0,
+  "total_flos": 783164469411840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null