Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9880f9a14e7e1b16646467ab0d161d117f1598c30881f29672a2b60ced9327ee
+oid sha256:51d535ba0e660420acdf72e7a6a0f5e895765af8e206cc752a5c2a10f730e283
 size 67662840

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb444bf5ba451c33cc607315d448f7fa02a9ff9b3bbe6e66bca96ebcbf0fa021
+oid sha256:86335376bbc378ffc6db3cd86237f4e02e04331ccfd8606fc3c0d43db50a728d
 size 34607610

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eca66d4a74945f7af156bf782963ee63f197435058aae7c08031504382213d7e
+oid sha256:340f6406b96d7e0f17315436c2bccb605d75c9d254ec958f91a4f659e4ffcdd7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85e9b4e25668eb135b65c8a2efd824713d5ec7e9a404d37d2fd3021c6e5610a3
+oid sha256:284a8517b2310fb02b51d6b8ddd318d3f6e139475d47fc950976ac1287debd43
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07352941176470588,
+  "epoch": 0.14705882352941177,
   "eval_steps": 1,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -82,6 +82,81 @@
       "eval_samples_per_second": 29.814,
       "eval_steps_per_second": 4.472,
       "step": 5
+    },
+    {
+      "epoch": 0.08823529411764706,
+      "grad_norm": 1.395002841949463,
+      "learning_rate": 3e-06,
+      "loss": 1.4327,
+      "step": 6
+    },
+    {
+      "epoch": 0.08823529411764706,
+      "eval_loss": 1.2674007415771484,
+      "eval_runtime": 2.5632,
+      "eval_samples_per_second": 39.013,
+      "eval_steps_per_second": 5.852,
+      "step": 6
+    },
+    {
+      "epoch": 0.10294117647058823,
+      "grad_norm": 1.0900819301605225,
+      "learning_rate": 3.5000000000000004e-06,
+      "loss": 1.2795,
+      "step": 7
+    },
+    {
+      "epoch": 0.10294117647058823,
+      "eval_loss": 1.269196629524231,
+      "eval_runtime": 2.4479,
+      "eval_samples_per_second": 40.852,
+      "eval_steps_per_second": 6.128,
+      "step": 7
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 1.7616393566131592,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.4695,
+      "step": 8
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "eval_loss": 1.267441749572754,
+      "eval_runtime": 2.4514,
+      "eval_samples_per_second": 40.792,
+      "eval_steps_per_second": 6.119,
+      "step": 8
+    },
+    {
+      "epoch": 0.1323529411764706,
+      "grad_norm": 1.3893433809280396,
+      "learning_rate": 4.5e-06,
+      "loss": 1.4243,
+      "step": 9
+    },
+    {
+      "epoch": 0.1323529411764706,
+      "eval_loss": 1.2656891345977783,
+      "eval_runtime": 3.1314,
+      "eval_samples_per_second": 31.934,
+      "eval_steps_per_second": 4.79,
+      "step": 9
+    },
+    {
+      "epoch": 0.14705882352941177,
+      "grad_norm": 1.2425161600112915,
+      "learning_rate": 5e-06,
+      "loss": 1.4099,
+      "step": 10
+    },
+    {
+      "epoch": 0.14705882352941177,
+      "eval_loss": 1.2637847661972046,
+      "eval_runtime": 2.4954,
+      "eval_samples_per_second": 40.074,
+      "eval_steps_per_second": 6.011,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -96,12 +171,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 314029414809600.0,
+  "total_flos": 628058829619200.0,
   "train_batch_size": 7,
   "trial_name": null,
   "trial_params": null