Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72b6679547d41816bbb20a19da912840978204f5ba607aae4f71273a1aefe616
+oid sha256:c12eec3d9555b262a7a1435cfafc62807f8cbebc1dc3693eef87cf3c48a6bbe3
 size 28348936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce905a8e92aa91a0952be0b183bd55dd759ad4c6eee72a5ad93f308306cb4575
+oid sha256:34c8afce54830e372f0c500c0f16ea0f923554f21caf1730b459cd6f071dd4ca
 size 14714004

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff226c15e19b8085e09f0025aa31f4d46c591e213735b264a5e28d7f9728a70c
+oid sha256:6011dbc1beaf916a24aa0692a7ad3787fe62f4d3127d9859b27643438838594d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0018971282221537148,
+  "epoch": 0.0037942564443074296,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 38.936,
       "eval_steps_per_second": 19.472,
       "step": 5
+    },
+    {
+      "epoch": 0.0022765538665844576,
+      "grad_norm": 1.0582722425460815,
+      "learning_rate": 6e-05,
+      "loss": 4.4896,
+      "step": 6
+    },
+    {
+      "epoch": 0.002655979511015201,
+      "grad_norm": 1.0632126331329346,
+      "learning_rate": 7e-05,
+      "loss": 4.4205,
+      "step": 7
+    },
+    {
+      "epoch": 0.0030354051554459436,
+      "grad_norm": 1.1783959865570068,
+      "learning_rate": 8e-05,
+      "loss": 4.3472,
+      "step": 8
+    },
+    {
+      "epoch": 0.003414830799876687,
+      "grad_norm": 1.0495206117630005,
+      "learning_rate": 9e-05,
+      "loss": 4.0192,
+      "step": 9
+    },
+    {
+      "epoch": 0.0037942564443074296,
+      "grad_norm": 1.5719696283340454,
+      "learning_rate": 0.0001,
+      "loss": 4.4723,
+      "step": 10
+    },
+    {
+      "epoch": 0.0037942564443074296,
+      "eval_loss": 4.074612140655518,
+      "eval_runtime": 114.2213,
+      "eval_samples_per_second": 38.863,
+      "eval_steps_per_second": 19.436,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 649047740252160.0,
+  "total_flos": 1298095480504320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null