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:a135aede87cda6ecfde1f70d0b3354148a37f949cd8ed501c8fb697ba40c82f1
+oid sha256:fd75d74313cede354e3941f73f3842af68de408eca240a13bca2aa0a207de9c0
 size 1912664024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c38f35188b582c0e79779b64a47af7f1dee72e35c6e27fe79eb27669d640453
+oid sha256:121c173b4e8064cbea232239a5ec74e0a24731ce43d30eab0717384e9d6f67c2
 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 sha256:2403ceb7668cef32f628e0206306d44446c6ca36607ab32d78706d484df089b1
+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": 3.817,
       "eval_steps_per_second": 0.496,
       "step": 40
+    },
+    {
+      "epoch": 0.003681207436039021,
+      "grad_norm": 0.08042994141578674,
+      "learning_rate": 0.00019977501431727072,
+      "loss": 2.0527,
+      "step": 60
+    },
+    {
+      "epoch": 0.003681207436039021,
+      "eval_loss": 1.9334843158721924,
+      "eval_runtime": 25.7281,
+      "eval_samples_per_second": 3.887,
+      "eval_steps_per_second": 0.505,
+      "step": 60
+    },
+    {
+      "epoch": 0.004908276581385361,
+      "grad_norm": 0.08663463592529297,
+      "learning_rate": 0.0001996932013417328,
+      "loss": 1.9392,
+      "step": 80
+    },
+    {
+      "epoch": 0.004908276581385361,
+      "eval_loss": 1.8688364028930664,
+      "eval_runtime": 26.145,
+      "eval_samples_per_second": 3.825,
+      "eval_steps_per_second": 0.497,
+      "step": 80
+    },
+    {
+      "epoch": 0.006135345726731701,
+      "grad_norm": 0.08462908118963242,
+      "learning_rate": 0.00019961138836619487,
+      "loss": 1.8772,
+      "step": 100
+    },
+    {
+      "epoch": 0.006135345726731701,
+      "eval_loss": 1.8178932666778564,
+      "eval_runtime": 26.3004,
+      "eval_samples_per_second": 3.802,
+      "eval_steps_per_second": 0.494,
+      "step": 100
     }
   ],
   "logging_steps": 20,
@@ -44,7 +89,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 50,
-  "total_flos": 3276518679244800.0,
+  "total_flos": 6919962687590400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null