Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:276f2a8994cfe821febcebef73f49c631dadfbe9f5aea69886da68df226b0446
+oid sha256:91094d08055e3e99fe094e0e373336458789e0997733b1ee0c88f128bc03ad3f
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94e3f3a2ce21d140b56527f4f67754dbecb87538c51ba12ab83aa34aecf737d7
+oid sha256:4d2ed57d6081b7d4a1ceec7332cb3bdef216f421efd9a0a8676dfb75e5e234e2
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aab570b4fe164a545749c52e1fee2e82c42fd074cc4792050df7927c2e3f881
+oid sha256:f4731a08616a258f51b82e9dd7d1ca90fe5909a76608a64af8bc3dc01ce461b8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03698435277382646,
+  "epoch": 0.07396870554765292,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 171.641,
       "eval_steps_per_second": 85.82,
       "step": 10
+    },
+    {
+      "epoch": 0.04267425320056899,
+      "grad_norm": 0.022381599992513657,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 10.3751,
+      "step": 15
+    },
+    {
+      "epoch": 0.05689900426742532,
+      "grad_norm": 0.02105828933417797,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 10.3762,
+      "step": 20
+    },
+    {
+      "epoch": 0.05689900426742532,
+      "eval_loss": 10.373991966247559,
+      "eval_runtime": 0.8862,
+      "eval_samples_per_second": 167.007,
+      "eval_steps_per_second": 83.503,
+      "step": 20
+    },
+    {
+      "epoch": 0.07112375533428165,
+      "grad_norm": 0.024705884978175163,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 10.3769,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 297410887680.0,
+  "total_flos": 578658140160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null