Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f69eeec3a62cc90812cd986360acca316172a0c1de19f581cff6f3265946fd2
+oid sha256:592ab26a2b97723a39c6ebf711264535154b01ae69104de25f0ab4d81a566e09
 size 119597408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cbefcd00d7b8fa00cb5f0cebb73040ace37ce7c7aaf971b4fd105e69e4e2e72
+oid sha256:821fd80c38d03c753fc6bc106fdaa21ba03f6ef3eb8f74d7ae2964902e6bfb63
 size 60386772

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 sha256:2403ceb7668cef32f628e0206306d44446c6ca36607ab32d78706d484df089b1
+oid sha256:3644cf9f8e3ac9f4f534109bec24dea135af8ce9e36c33ebe8e1053def47661f
 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": 5.091,
       "eval_steps_per_second": 0.662,
       "step": 40
+    },
+    {
+      "epoch": 0.003681207436039021,
+      "grad_norm": 0.8112285733222961,
+      "learning_rate": 0.00019977501431727072,
+      "loss": 1.9429,
+      "step": 60
+    },
+    {
+      "epoch": 0.003681207436039021,
+      "eval_loss": 1.8300584554672241,
+      "eval_runtime": 19.6764,
+      "eval_samples_per_second": 5.082,
+      "eval_steps_per_second": 0.661,
+      "step": 60
+    },
+    {
+      "epoch": 0.004908276581385361,
+      "grad_norm": 0.7514470219612122,
+      "learning_rate": 0.0001996932013417328,
+      "loss": 1.8545,
+      "step": 80
+    },
+    {
+      "epoch": 0.004908276581385361,
+      "eval_loss": 1.7825714349746704,
+      "eval_runtime": 19.7307,
+      "eval_samples_per_second": 5.068,
+      "eval_steps_per_second": 0.659,
+      "step": 80
+    },
+    {
+      "epoch": 0.006135345726731701,
+      "grad_norm": 0.6156793832778931,
+      "learning_rate": 0.00019961138836619487,
+      "loss": 1.8015,
+      "step": 100
+    },
+    {
+      "epoch": 0.006135345726731701,
+      "eval_loss": 1.7314132452011108,
+      "eval_runtime": 19.6578,
+      "eval_samples_per_second": 5.087,
+      "eval_steps_per_second": 0.661,
+      "step": 100
     }
   ],
   "logging_steps": 20,
@@ -44,7 +89,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 50,
-  "total_flos": 2926876391239680.0,
+  "total_flos": 6169094793400320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null