Training in progress, epoch 3, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a1f073919e39f64dce51758a5a2e8f28ba21b49f4d80eb41fb393b9628c81e9
+oid sha256:de5dc81cffd65b4c80541865d2dbc3f5e12bccb55856added53bc35419f6fd14
 size 27280152

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad4381a085d788645fec01a564cb990e81ce1bc63f11b52c1716e0d2dad90e62
+oid sha256:88946ac662d99a1e4de0bf5ee29eb8393a830132079c60f908fbd3a1d2acea94
 size 54602042

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b912d070553f91b45824b99185d735298ee3216329352a3dc84c5dccab8294cc
+oid sha256:8c2316c8d86b2e1ca0ca53dcdc663720462797db5c48b195cb53856bbce5aaaa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c25a29b379986fd5fdbdcc9bd4405310ea3d8c6f12bce6627e781132dfed654
+oid sha256:1f802f704a3eeb43f74ed18effaa9875c60ab434e09051037a5be7b9b680e9c2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 116,
+  "global_step": 174,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -51,6 +51,28 @@
       "eval_samples_per_second": 2.406,
       "eval_steps_per_second": 0.314,
       "step": 116
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.23599840700626373,
+      "learning_rate": 4.045396755473121e-05,
+      "loss": 0.2321,
+      "step": 125
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 0.2667102813720703,
+      "learning_rate": 1.026015713086418e-05,
+      "loss": 0.2281,
+      "step": 150
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.24546320736408234,
+      "eval_runtime": 47.8298,
+      "eval_samples_per_second": 2.404,
+      "eval_steps_per_second": 0.314,
+      "step": 174
     }
   ],
   "logging_steps": 25,
@@ -58,7 +80,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 2.007196514648064e+16,
+  "total_flos": 3.010794771972096e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null