Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9686c21461e16fb228541d5cce58d6da64d0a3f7014c0f6bf570dd1823a6650f
+oid sha256:bb4d3f9835836764b228a24ed5de764b0c80ca3ff41cdc154c00897b2f75e9a3
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dc2a92d452e5b66a6f9f09f33290457cd796113555c56730ba7cba4f04199f8
+oid sha256:51fe03aa815c27042d68618b4e387de8d8abbc52b913e3d60bd429d7430f3a26
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2887bcfdd83964510fb69a5570e8390fa9b460bc5dbd4d19622dd266c080d238
+oid sha256:556ad3e4fe6133676884b85c9c7e60afe47ffdaad90a4ce5f041a069278ef787
 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": 0.000632211158526948,
+  "epoch": 0.001264422317053896,
   "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": 4.343,
       "eval_steps_per_second": 2.171,
       "step": 15
+    },
+    {
+      "epoch": 0.0007586533902323376,
+      "grad_norm": 0.596531093120575,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 2.9737,
+      "step": 18
+    },
+    {
+      "epoch": 0.000842948211369264,
+      "eval_loss": 0.6829288005828857,
+      "eval_runtime": 2300.8333,
+      "eval_samples_per_second": 4.342,
+      "eval_steps_per_second": 2.171,
+      "step": 20
+    },
+    {
+      "epoch": 0.0008850956219377273,
+      "grad_norm": 0.5559117794036865,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.6243,
+      "step": 21
+    },
+    {
+      "epoch": 0.0010115378536431168,
+      "grad_norm": 0.5070546865463257,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.6916,
+      "step": 24
+    },
+    {
+      "epoch": 0.00105368526421158,
+      "eval_loss": 0.6756637692451477,
+      "eval_runtime": 2301.5264,
+      "eval_samples_per_second": 4.341,
+      "eval_steps_per_second": 2.17,
+      "step": 25
+    },
+    {
+      "epoch": 0.0011379800853485065,
+      "grad_norm": 0.643730103969574,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.6812,
+      "step": 27
+    },
+    {
+      "epoch": 0.001264422317053896,
+      "grad_norm": 0.4069077670574188,
+      "learning_rate": 0.0,
+      "loss": 2.6433,
+      "step": 30
+    },
+    {
+      "epoch": 0.001264422317053896,
+      "eval_loss": 0.673958420753479,
+      "eval_runtime": 2297.5409,
+      "eval_samples_per_second": 4.348,
+      "eval_steps_per_second": 2.174,
+      "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": 1.840870689079296e+16,
+  "total_flos": 3.65000222834688e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null