Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8c5b3b034751f4e0690381137d838944d1617619e3482f3b30a57eed1b17b1e
+oid sha256:e621edb8f9d2e3b44be10e33f537f26ac1ba0d2c41b3b7762f7d94ec439a38c5
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:677af05485e04a18a644a268b3f2277d41b75aac4284a5d334410f36d81d5e86
+oid sha256:9cf11d2a5209b8d03328f03a5db4507208b96aec65ecdde5e845b1cf3b6a3db6
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09c493f63412e264b3a37fdcb8df0f0fb81fcec9f3ff13481c080d7a222d6915
+oid sha256:75080ec56518801d1d6c91757a4dc9a773c5629443c6668a848998562bf287d8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
+oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0027711385915688107,
+  "epoch": 0.003694851455425081,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 13.713,
       "eval_steps_per_second": 6.857,
       "step": 15
+    },
+    {
+      "epoch": 0.002955881164340065,
+      "grad_norm": 35.03306198120117,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 63.2034,
+      "step": 16
+    },
+    {
+      "epoch": 0.003140623737111319,
+      "grad_norm": 32.41392517089844,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 56.0369,
+      "step": 17
+    },
+    {
+      "epoch": 0.003325366309882573,
+      "grad_norm": 32.28781509399414,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 59.4549,
+      "step": 18
+    },
+    {
+      "epoch": 0.0035101088826538273,
+      "grad_norm": 32.226200103759766,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 63.0719,
+      "step": 19
+    },
+    {
+      "epoch": 0.003694851455425081,
+      "grad_norm": 32.14451217651367,
+      "learning_rate": 0.0,
+      "loss": 56.4091,
+      "step": 20
+    },
+    {
+      "epoch": 0.003694851455425081,
+      "eval_loss": 3.589934825897217,
+      "eval_runtime": 2227.8468,
+      "eval_samples_per_second": 4.092,
+      "eval_steps_per_second": 2.046,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.978890190848e+16,
+  "total_flos": 2.659628416499712e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null