Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:885863153bfb83203fdbc97afdcb5aee040d040888095c316663501d4bab8f16
+oid sha256:90f8601b71f80088c08b663ad2fca2d1d34596e28f87bb041f152b901dd997c6
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6913015b98979b36dac3c84bce0df6ee29ea1f616aa9a86a1b22348060f836d2
+oid sha256:bc2f781ef19c859fbd12d423d634672c500d14767189ba1a4d0fdb62bab76466
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a349f547bb0c5e89e400b9c38fa77cae9d6e62e339f06e2e955296b86da35cc
+oid sha256:93159e748760564f8ab001b1ac34d31130729a4daae6ec52572e87ec6f8cc715
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef527702b4e2147a500c0b29beb26751d245ebb60338b3910b449b6549ac4d59
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01670378619153675,
+  "epoch": 0.0334075723830735,
   "eval_steps": 8,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,57 @@
       "learning_rate": 0.0002,
       "loss": 4.2514,
       "step": 15
+    },
+    {
+      "epoch": 0.017817371937639197,
+      "eval_loss": 1.1712861061096191,
+      "eval_runtime": 46.2407,
+      "eval_samples_per_second": 6.142,
+      "eval_steps_per_second": 3.071,
+      "step": 16
+    },
+    {
+      "epoch": 0.0200445434298441,
+      "grad_norm": 3.744047164916992,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 3.8414,
+      "step": 18
+    },
+    {
+      "epoch": 0.02338530066815145,
+      "grad_norm": 3.7839925289154053,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.123,
+      "step": 21
+    },
+    {
+      "epoch": 0.026726057906458798,
+      "grad_norm": 6.720678806304932,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.907,
+      "step": 24
+    },
+    {
+      "epoch": 0.026726057906458798,
+      "eval_loss": 0.8629888296127319,
+      "eval_runtime": 46.2538,
+      "eval_samples_per_second": 6.14,
+      "eval_steps_per_second": 3.07,
+      "step": 24
+    },
+    {
+      "epoch": 0.030066815144766147,
+      "grad_norm": 3.833301305770874,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.6673,
+      "step": 27
+    },
+    {
+      "epoch": 0.0334075723830735,
+      "grad_norm": 3.1711502075195312,
+      "learning_rate": 0.0,
+      "loss": 2.6537,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -72,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7141308707635200.0,
+  "total_flos": 1.42826174152704e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null