Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d918b445e9c66a0ce0e4e84d9061fa2984ef4baa2b691afe223994e68094059d
+oid sha256:b3709347ce16f46bd796f8841820e9118de975896347b79bb64b2e9d865bb853
 size 1912664024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:420ae61f406a1716b041f637974c538814787f0c36b6cb165d38598f7461778f
+oid sha256:be402730e78db70767a9527ae87662e894557ab8e2016ba216dca11054b5eecf
 size 958697364

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:376fa8cdca401e75879a433c4cf57e5c31b5973d7635f7e690ffeb05b513101b
+oid sha256:842666bae3e6d50174909a214b88b57822ee9f4eb536e3ad5a5e1b5cac198a06
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43eaf6e8b9b7e97d802563efbae1976d32c9bf9869f2ff306873ea7672065324
+oid sha256:3e92f0f397b9b038f45c11752b97df406ae4c48a13239b85496df77bbd655068
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0030676728633658506,
+  "epoch": 0.006135345726731701,
   "eval_steps": 20,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,51 @@
       "eval_samples_per_second": 4.217,
       "eval_steps_per_second": 0.548,
       "step": 40
+    },
+    {
+      "epoch": 0.003681207436039021,
+      "grad_norm": 0.1341264545917511,
+      "learning_rate": 0.00019932490487295938,
+      "loss": 1.9978,
+      "step": 60
+    },
+    {
+      "epoch": 0.003681207436039021,
+      "eval_loss": 1.8857674598693848,
+      "eval_runtime": 24.0663,
+      "eval_samples_per_second": 4.155,
+      "eval_steps_per_second": 0.54,
+      "step": 60
+    },
+    {
+      "epoch": 0.004908276581385361,
+      "grad_norm": 0.13033552467823029,
+      "learning_rate": 0.00019907941573585368,
+      "loss": 1.8977,
+      "step": 80
+    },
+    {
+      "epoch": 0.004908276581385361,
+      "eval_loss": 1.8246879577636719,
+      "eval_runtime": 23.578,
+      "eval_samples_per_second": 4.241,
+      "eval_steps_per_second": 0.551,
+      "step": 80
+    },
+    {
+      "epoch": 0.006135345726731701,
+      "grad_norm": 0.11537110805511475,
+      "learning_rate": 0.00019883392659874802,
+      "loss": 1.8383,
+      "step": 100
+    },
+    {
+      "epoch": 0.006135345726731701,
+      "eval_loss": 1.7761367559432983,
+      "eval_runtime": 23.7248,
+      "eval_samples_per_second": 4.215,
+      "eval_steps_per_second": 0.548,
+      "step": 100
     }
   ],
   "logging_steps": 20,
@@ -44,7 +89,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 50,
-  "total_flos": 3276518679244800.0,
+  "total_flos": 6919962687590400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null