Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a19207b364b4ceaa4ae9ff9ae5dadfb6e48c04ca3d885c035099c9cd335421d
+oid sha256:9d3f49076607b763eaf860c1556d5a8f4445ad7058bd2a7db28bc02ae6f09242
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d36db95ac373abc14a4f17d451e6f68064999bdac822283066efc750d77dce9e
+oid sha256:9355ace4e70609cee3c20d13b58905ef6f38c18a5b75d0b0291aafcc2025d1a3
 size 166439638

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eefaa47e55c8b641285f20788c3c6ccb8efe04d5676c94fb09af90185b85664
+oid sha256:75caa14d0693086c5957e78bfabc5e03e26e0a02e3ebab6e9c7167f2b79dbe10
 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": 0.0025497195308516064,
+  "epoch": 0.005099439061703213,
   "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": 3.8098,
       "step": 15
+    },
+    {
+      "epoch": 0.00271970083290838,
+      "eval_loss": 3.7903103828430176,
+      "eval_runtime": 99.4808,
+      "eval_samples_per_second": 18.677,
+      "eval_steps_per_second": 9.338,
+      "step": 16
+    },
+    {
+      "epoch": 0.0030596634370219276,
+      "grad_norm": 2.815793514251709,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 3.643,
+      "step": 18
+    },
+    {
+      "epoch": 0.0035696073431922487,
+      "grad_norm": 3.6142284870147705,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.7735,
+      "step": 21
+    },
+    {
+      "epoch": 0.00407955124936257,
+      "grad_norm": 3.6628382205963135,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 3.765,
+      "step": 24
+    },
+    {
+      "epoch": 0.00407955124936257,
+      "eval_loss": 3.536585807800293,
+      "eval_runtime": 99.3773,
+      "eval_samples_per_second": 18.696,
+      "eval_steps_per_second": 9.348,
+      "step": 24
+    },
+    {
+      "epoch": 0.004589495155532891,
+      "grad_norm": 3.4352312088012695,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 3.5037,
+      "step": 27
+    },
+    {
+      "epoch": 0.005099439061703213,
+      "grad_norm": 3.9947495460510254,
+      "learning_rate": 0.0,
+      "loss": 3.3895,
+      "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": 1130960576839680.0,
+  "total_flos": 2261921153679360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null