Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd75d74313cede354e3941f73f3842af68de408eca240a13bca2aa0a207de9c0
+oid sha256:419ef2c365b2df61990765df67db820969667778e123c6c39e29b83cc59610e1
 size 1912664024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:121c173b4e8064cbea232239a5ec74e0a24731ce43d30eab0717384e9d6f67c2
+oid sha256:ceafd3de144036993fa29e2a17c0194470e240a1f774ed6130da298efb1038af
 size 958697364

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:842666bae3e6d50174909a214b88b57822ee9f4eb536e3ad5a5e1b5cac198a06
+oid sha256:399c6e0a1a129bcf47d55d6652cc4710de81e426cb3bb5b9430151acfb862766
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3644cf9f8e3ac9f4f534109bec24dea135af8ce9e36c33ebe8e1053def47661f
+oid sha256:857bbe62f2d165935d1ce9ae82dd80a72b9db823aa28c4ae95a8b905e80accaa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006135345726731701,
+  "epoch": 0.009203018590097553,
   "eval_steps": 20,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -82,6 +82,36 @@
       "eval_samples_per_second": 3.802,
       "eval_steps_per_second": 0.494,
       "step": 100
+    },
+    {
+      "epoch": 0.007362414872078042,
+      "grad_norm": 0.11603377014398575,
+      "learning_rate": 0.000199529575390657,
+      "loss": 1.7827,
+      "step": 120
+    },
+    {
+      "epoch": 0.007362414872078042,
+      "eval_loss": 1.773740291595459,
+      "eval_runtime": 26.4277,
+      "eval_samples_per_second": 3.784,
+      "eval_steps_per_second": 0.492,
+      "step": 120
+    },
+    {
+      "epoch": 0.008589484017424381,
+      "grad_norm": 0.10753527283668518,
+      "learning_rate": 0.00019944776241511905,
+      "loss": 1.8118,
+      "step": 140
+    },
+    {
+      "epoch": 0.008589484017424381,
+      "eval_loss": 1.7376396656036377,
+      "eval_runtime": 26.2097,
+      "eval_samples_per_second": 3.815,
+      "eval_steps_per_second": 0.496,
+      "step": 140
     }
   ],
   "logging_steps": 20,
@@ -89,7 +119,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 50,
-  "total_flos": 6919962687590400.0,
+  "total_flos": 1.02462852169728e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null