Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f68a16d50c9aa81b270a5135684253efe608051ac965a02fcd30e70b7eea3a8
+oid sha256:7f79c6f46e9e1f540e7c2a24956826d4055294eb7cda4654861eb503f283faf6
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8804e82d65ab3649fad430f8cbc7efd5a82e3274ec426a5d59996c27ad651249
+oid sha256:f899b0ad8da6da08a11dc3c0484d2a21d4c3c58e590a6827122cf5d521c3e5f0
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dca3e02eebe83d24045a6a34961b86f2d2953f340af948f4ff2d9c1cc24f691a
+oid sha256:d52de5368f5ce61262c2d589ee36ea6650cbb194994badad3cc71c4ee2f14c31
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8148b27980adb9b0bdd5c04049e531bfefcc05c06612ee72169cfb9b9fd7ee7
+oid sha256:0fd8212ec5ec3406d74a7f927b717dd30ea8a06115ee6582e14976f7b84b4b58
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0099000099000099,
+  "epoch": 0.0198000198000198,
   "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": 11.889,
       "eval_steps_per_second": 5.948,
       "step": 50
+    },
+    {
+      "epoch": 0.01188001188001188,
+      "grad_norm": 1.6590255498886108,
+      "learning_rate": 0.00016324453755953773,
+      "loss": 3.7843,
+      "step": 60
+    },
+    {
+      "epoch": 0.01386001386001386,
+      "grad_norm": 1.043177843093872,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 3.9678,
+      "step": 70
+    },
+    {
+      "epoch": 0.01584001584001584,
+      "grad_norm": 1.2934823036193848,
+      "learning_rate": 0.00013546048870425356,
+      "loss": 3.5944,
+      "step": 80
+    },
+    {
+      "epoch": 0.01782001782001782,
+      "grad_norm": 2.192728281021118,
+      "learning_rate": 0.00012000256937760445,
+      "loss": 3.5243,
+      "step": 90
+    },
+    {
+      "epoch": 0.0198000198000198,
+      "grad_norm": 0.9403907060623169,
+      "learning_rate": 0.00010402659401094152,
+      "loss": 3.4414,
+      "step": 100
+    },
+    {
+      "epoch": 0.0198000198000198,
+      "eval_loss": 0.860140323638916,
+      "eval_runtime": 179.0977,
+      "eval_samples_per_second": 11.876,
+      "eval_steps_per_second": 5.941,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.430077154361344e+16,
+  "total_flos": 4.883900991012864e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null