Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d448ed0eb63fb8ce796a2581a39a0989adf0f3fdc057758e65f7b276b4a7621
+oid sha256:cf9902b37fdf30bd898e72e062032368ce7d3124d27defa06d740efe280dc41d
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d317dc7f642fe19af067cb4a47a5dfb0a5d3f563e97db730ffcfb5ee3f8999f
+oid sha256:f8fe13c1088b03e11a3d5905d908bcc33c1f9e0792d459d74980c963162b3a66
 size 70922

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34bbf0a182beb8b828664678e023a763c79c30da1ab16c76d1c95f00474ec9ee
+oid sha256:63076df0e2f5c2eff0ee92071ec83ec94c981f8fbd2f640764417db149cee50d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab098d97568c94b26c087e3ff4fd649c3aaa775049e6dbf18e927dde2c5feee8
+oid sha256:06829946ff807c7143728448cc1bf384944e638865601317db4b29a92003bb11
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003418803418803419,
+  "epoch": 0.006837606837606838,
   "eval_steps": 2,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -66,6 +66,65 @@
       "learning_rate": 0.0001,
       "loss": 10.3781,
       "step": 5
+    },
+    {
+      "epoch": 0.0041025641025641026,
+      "grad_norm": 0.012160197831690311,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 10.3803,
+      "step": 6
+    },
+    {
+      "epoch": 0.0041025641025641026,
+      "eval_loss": 10.379097938537598,
+      "eval_runtime": 3.6086,
+      "eval_samples_per_second": 170.703,
+      "eval_steps_per_second": 85.352,
+      "step": 6
+    },
+    {
+      "epoch": 0.004786324786324786,
+      "grad_norm": 0.01298796571791172,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 10.3767,
+      "step": 7
+    },
+    {
+      "epoch": 0.00547008547008547,
+      "grad_norm": 0.012850708328187466,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 10.3795,
+      "step": 8
+    },
+    {
+      "epoch": 0.00547008547008547,
+      "eval_loss": 10.379048347473145,
+      "eval_runtime": 3.5895,
+      "eval_samples_per_second": 171.61,
+      "eval_steps_per_second": 85.805,
+      "step": 8
+    },
+    {
+      "epoch": 0.006153846153846154,
+      "grad_norm": 0.013943369500339031,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 10.3819,
+      "step": 9
+    },
+    {
+      "epoch": 0.006837606837606838,
+      "grad_norm": 0.017278488725423813,
+      "learning_rate": 5e-05,
+      "loss": 10.3765,
+      "step": 10
+    },
+    {
+      "epoch": 0.006837606837606838,
+      "eval_loss": 10.379008293151855,
+      "eval_runtime": 3.566,
+      "eval_samples_per_second": 172.744,
+      "eval_steps_per_second": 86.372,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -85,7 +144,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 258618163200.0,
+  "total_flos": 517236326400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null