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:e90b1c0dba55e43621bde84dea504dec20fd817f2baf349408a4fbe061226e66
+oid sha256:9a98731743092092fa09da85913866df67fe644c0b4e279dc90761934cd6cf5a
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6c7a12f60b75ac54c13466425236e9f6205918af29d0964e789d0b38d85deca
+oid sha256:08341b68241dc281c40a6469e7efa6f0f4e26b7dafc0fbdbf6ab0bf7c7267de8
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03c61da2a72ba214c944d958fb36272fb6382ce5fcbfecf19eac7eeb12869a37
+oid sha256:8f9113e1eb32f6a8faa87851ebb8b8eebb4dee14e16a8f7564c198b2fb33406f
 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": 0.008771929824561403,
+  "epoch": 0.017543859649122806,
   "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": 4.9818,
       "step": 15
+    },
+    {
+      "epoch": 0.00935672514619883,
+      "eval_loss": 1.5126136541366577,
+      "eval_runtime": 40.2642,
+      "eval_samples_per_second": 13.411,
+      "eval_steps_per_second": 6.706,
+      "step": 16
+    },
+    {
+      "epoch": 0.010526315789473684,
+      "grad_norm": 1.0104972124099731,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 4.7518,
+      "step": 18
+    },
+    {
+      "epoch": 0.012280701754385965,
+      "grad_norm": 1.0568211078643799,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 4.4204,
+      "step": 21
+    },
+    {
+      "epoch": 0.014035087719298246,
+      "grad_norm": 0.7512881755828857,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 4.513,
+      "step": 24
+    },
+    {
+      "epoch": 0.014035087719298246,
+      "eval_loss": 1.489016056060791,
+      "eval_runtime": 40.2262,
+      "eval_samples_per_second": 13.424,
+      "eval_steps_per_second": 6.712,
+      "step": 24
+    },
+    {
+      "epoch": 0.015789473684210527,
+      "grad_norm": 0.8052785396575928,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 4.4545,
+      "step": 27
+    },
+    {
+      "epoch": 0.017543859649122806,
+      "grad_norm": 0.7201788425445557,
+      "learning_rate": 0.0,
+      "loss": 4.5524,
+      "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": 2072352946913280.0,
+  "total_flos": 4144705893826560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null