Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4862d0db4549bad7b9d71ad9f351c7b339cadeaf070335fddf54097fd9f8a191
+oid sha256:71e38be8cd3e1789ae3735b27b93488654df375a71639ec1f526d2c27acecfe1
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11637d90566b0d7121c436085f3121556eeaaaa5fab32094264a53f19e56126e
+oid sha256:6458122ec561144054fbf12a86dc7bb4c1b34b06bc5aec29eed362d2529c40b9
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:134d324e84bd4fce28c794aaa5abd5c0a556e722fd69691d0e1729b81b8cfede
+oid sha256:e09f9d8c9e048830f98d8554060bfff7f6550357d501c02f1cbd2ff879b1e61e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b80fcc7599efca0c6313d990c467c2eb3001742b23ddaadc22e3499c12cea79
+oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003514629645901063,
+  "epoch": 0.007029259291802126,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 16.671,
       "eval_steps_per_second": 8.336,
       "step": 50
+    },
+    {
+      "epoch": 0.004217555575081276,
+      "grad_norm": 14.511041641235352,
+      "learning_rate": 0.0002,
+      "loss": 4.2254,
+      "step": 60
+    },
+    {
+      "epoch": 0.0049204815042614885,
+      "grad_norm": 22.804845809936523,
+      "learning_rate": 0.0002,
+      "loss": 4.2431,
+      "step": 70
+    },
+    {
+      "epoch": 0.005623407433441701,
+      "grad_norm": 34.24738693237305,
+      "learning_rate": 0.0002,
+      "loss": 4.3371,
+      "step": 80
+    },
+    {
+      "epoch": 0.006326333362621913,
+      "grad_norm": 12.90673542022705,
+      "learning_rate": 0.0002,
+      "loss": 4.0954,
+      "step": 90
+    },
+    {
+      "epoch": 0.007029259291802126,
+      "grad_norm": 14.861096382141113,
+      "learning_rate": 0.0002,
+      "loss": 4.3418,
+      "step": 100
+    },
+    {
+      "epoch": 0.007029259291802126,
+      "eval_loss": 1.05625581741333,
+      "eval_runtime": 358.9389,
+      "eval_samples_per_second": 16.688,
+      "eval_steps_per_second": 8.344,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5379677371695104e+16,
+  "total_flos": 3.0715537998741504e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null