Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82b51046a8d00417759e84270900ac6ceab34e6c16e46ba68b7abf726a7ec109
+oid sha256:57e9cb39520de6c97dd8daa6d7fe73a7d1db36c97e4373a9ab4bd9c390e52c11
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2210f6df71337585112d1a97a6545f1cc729aa58cc5d0c05b0b8a131a612389
+oid sha256:4eb90ae6d929a5bea3d77e0fca83076b4ebaf0255298cce0eda9a9957e793c5e
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35d8cf5074f008d9ff56aa6278641e57385099fe8d5c83cc4cdf7e38c4be8d2e
+oid sha256:579360aedf9e1e6d78ecaf690eee9abae295d9f1032a5ecb7ca3cda426db0d8f
 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": 0.009528346831824679,
+  "epoch": 0.019056693663649357,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,28 @@
       "eval_samples_per_second": 6.285,
       "eval_steps_per_second": 0.789,
       "step": 5
+    },
+    {
+      "epoch": 0.011434016198189614,
+      "grad_norm": 1.5631052255630493,
+      "learning_rate": 6e-05,
+      "loss": 2.8163,
+      "step": 6
+    },
+    {
+      "epoch": 0.01715102429728442,
+      "grad_norm": 1.3446643352508545,
+      "learning_rate": 9e-05,
+      "loss": 2.5454,
+      "step": 9
+    },
+    {
+      "epoch": 0.019056693663649357,
+      "eval_loss": 2.5639851093292236,
+      "eval_runtime": 140.6263,
+      "eval_samples_per_second": 6.286,
+      "eval_steps_per_second": 0.789,
+      "step": 10
     }
   ],
   "logging_steps": 3,
@@ -49,7 +71,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.508513578745856e+16,
+  "total_flos": 3.017027157491712e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null