Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b238847b847a58725cdad4fe7921c839e6f9a7be203b578b0ad642748d7aed3
+oid sha256:e512d814f6ef2016bc08da14bc1d5e90fcbb4a34d314b9c716933076da7a83d7
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a66af16bba0eaeedb7440bdfa5c57d13a764d6e4abb518aea3b2eaa458319624
+oid sha256:459181f59d58dea842ede88438f4a450e18f01a48468efc7d3e28b9e6dd7eb4f
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3b91b616bd452b894e1aea50022754f9be4afc2c867b79623be361a63b980b2
+oid sha256:df2eff7fc04c424d03efebb207948c12df40c4005d61c167cc0982b8e6c469d5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
+oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004268943436499467,
+  "epoch": 0.0064034151547491995,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 386.018,
       "eval_steps_per_second": 193.009,
       "step": 100
+    },
+    {
+      "epoch": 0.004695837780149413,
+      "grad_norm": 0.8417938947677612,
+      "learning_rate": 0.0002,
+      "loss": 43.525,
+      "step": 110
+    },
+    {
+      "epoch": 0.005122732123799359,
+      "grad_norm": 0.7629103660583496,
+      "learning_rate": 0.0002,
+      "loss": 43.5057,
+      "step": 120
+    },
+    {
+      "epoch": 0.005549626467449306,
+      "grad_norm": 0.763012170791626,
+      "learning_rate": 0.0002,
+      "loss": 43.4606,
+      "step": 130
+    },
+    {
+      "epoch": 0.005976520811099253,
+      "grad_norm": 0.8534968495368958,
+      "learning_rate": 0.0002,
+      "loss": 43.4568,
+      "step": 140
+    },
+    {
+      "epoch": 0.0064034151547491995,
+      "grad_norm": 0.9974360466003418,
+      "learning_rate": 0.0002,
+      "loss": 43.4598,
+      "step": 150
+    },
+    {
+      "epoch": 0.0064034151547491995,
+      "eval_loss": 10.865395545959473,
+      "eval_runtime": 25.6883,
+      "eval_samples_per_second": 383.987,
+      "eval_steps_per_second": 191.994,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1357505888256.0,
+  "total_flos": 2030230831104.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null