Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:615efcf6770f15c75b36dc895b846eed554562d63b7b6d58d78c0d624b2d1fc6
+oid sha256:2812bef2c06270dfb9088cb85b06f499acb5d8f2e0e49fb9244000a199ca1ebf
 size 159712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56dd26b2e458a8a8dada5c0c943fec6986c0df18166a8fb3148bae8fad5c9d45
+oid sha256:a4286cb538ee2c6fe5ad8cce7c0a660ad8cd0264b902b06a659a3b73d606700d
 size 336202

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22cdbc90fe5ab190ddc8c8d596470e7106be9ee2374df85af28061b6a32f91c4
+oid sha256:4542ee77b862586921f712605c9da4a157f7c6fb74687d0b6cef8d69e7a87363
 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": 0.0020602980564521666,
+  "epoch": 0.004120596112904333,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,65 @@
       "eval_samples_per_second": 236.505,
       "eval_steps_per_second": 118.252,
       "step": 15
+    },
+    {
+      "epoch": 0.0024723576677426,
+      "grad_norm": 0.19254495203495026,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 10.8235,
+      "step": 18
+    },
+    {
+      "epoch": 0.002747064075269556,
+      "eval_loss": 10.819356918334961,
+      "eval_runtime": 13.0087,
+      "eval_samples_per_second": 235.689,
+      "eval_steps_per_second": 117.844,
+      "step": 20
+    },
+    {
+      "epoch": 0.0028844172790330335,
+      "grad_norm": 0.1905592381954193,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.8209,
+      "step": 21
+    },
+    {
+      "epoch": 0.003296476890323467,
+      "grad_norm": 0.18835890293121338,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 10.8132,
+      "step": 24
+    },
+    {
+      "epoch": 0.0034338300940869445,
+      "eval_loss": 10.814057350158691,
+      "eval_runtime": 12.884,
+      "eval_samples_per_second": 237.969,
+      "eval_steps_per_second": 118.984,
+      "step": 25
+    },
+    {
+      "epoch": 0.0037085365016139003,
+      "grad_norm": 0.28516891598701477,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 10.8092,
+      "step": 27
+    },
+    {
+      "epoch": 0.004120596112904333,
+      "grad_norm": 0.23441976308822632,
+      "learning_rate": 0.0,
+      "loss": 10.8112,
+      "step": 30
+    },
+    {
+      "epoch": 0.004120596112904333,
+      "eval_loss": 10.812871932983398,
+      "eval_runtime": 12.8772,
+      "eval_samples_per_second": 238.096,
+      "eval_steps_per_second": 119.048,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -88,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3094098739200.0,
+  "total_flos": 6188197478400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null