Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9edf97282e0e32622b05549075808334b8b7ddc755a5faf17f1db4272afdd90b
+oid sha256:9581f3a1ffe4b014ff23e85f03e1f36e87334d73bd1eeee448562b64ddaebdbf
 size 217931936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd03220a6e9d335dd2e6478377c8c9cd8e77cd1efa9df94afbf28dc03ffa30cd
+oid sha256:9251dc95a4d38de1cfece21a2e4432e048e7a2f7eca93e82aa6550a945a1592c
 size 436251442

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f1e5210a7dc83e89b360cf05e7c8b88a59631552775cb8c7a90249f1dcc3be6
+oid sha256:baddb4a0d1936cf0dd7742a6ecd73142598d50bc9bda5caab9e822d9997ce1e1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010089544709294993,
+  "epoch": 0.01513431706394249,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 5.029,
       "eval_steps_per_second": 2.518,
       "step": 20
+    },
+    {
+      "epoch": 0.010594021944759743,
+      "grad_norm": 0.5030087232589722,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.1613,
+      "step": 21
+    },
+    {
+      "epoch": 0.012107453651153992,
+      "grad_norm": 0.3733592927455902,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.0459,
+      "step": 24
+    },
+    {
+      "epoch": 0.01261193088661874,
+      "eval_loss": 1.1298078298568726,
+      "eval_runtime": 166.0968,
+      "eval_samples_per_second": 5.027,
+      "eval_steps_per_second": 2.517,
+      "step": 25
+    },
+    {
+      "epoch": 0.01362088535754824,
+      "grad_norm": 0.43001943826675415,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.1579,
+      "step": 27
+    },
+    {
+      "epoch": 0.01513431706394249,
+      "grad_norm": 0.3514871299266815,
+      "learning_rate": 0.0,
+      "loss": 1.0653,
+      "step": 30
+    },
+    {
+      "epoch": 0.01513431706394249,
+      "eval_loss": 1.123421549797058,
+      "eval_runtime": 166.0071,
+      "eval_samples_per_second": 5.03,
+      "eval_steps_per_second": 2.518,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.536184232706048e+16,
+  "total_flos": 2.330762284105728e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null