Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d898712c150bbdc4e4638c28c56eb205a6d2ea591c22037f9a4826ec0765d005
+oid sha256:d3be737cc5356b37c499bd42439c56e738423bea60daf3ef045d50d90d5e7b10
 size 5327496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d464fde61dbbb120c2722503afde5f79f24c933cc8fb3694e7f15b67bd4bb49b
+oid sha256:f68b5296ee5d096d667b7c7497c547fa914d2fba780393f990782056895603b0
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfdffa00fcbf23263244b002c2645ff4c50ab2041c7b30ed2dd004479b2b5f47
+oid sha256:a7457b321210c790e6a14c8eb3d204a278522711d3ddc1f831e3f3d1fbde7bc6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00047975052972454323,
+  "epoch": 0.0007196257945868149,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 108.079,
       "eval_steps_per_second": 54.039,
       "step": 6
+    },
+    {
+      "epoch": 0.0005597089513453004,
+      "grad_norm": 0.7125624418258667,
+      "learning_rate": 0.00014,
+      "loss": 2.5858,
+      "step": 7
+    },
+    {
+      "epoch": 0.0006396673729660577,
+      "grad_norm": 1.5198544263839722,
+      "learning_rate": 0.00016,
+      "loss": 8.0022,
+      "step": 8
+    },
+    {
+      "epoch": 0.0007196257945868149,
+      "grad_norm": 1.132773756980896,
+      "learning_rate": 0.00018,
+      "loss": 5.0194,
+      "step": 9
+    },
+    {
+      "epoch": 0.0007196257945868149,
+      "eval_loss": 0.6932116746902466,
+      "eval_runtime": 48.2958,
+      "eval_samples_per_second": 109.036,
+      "eval_steps_per_second": 54.518,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 16447605571584.0,
+  "total_flos": 24936692318208.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null