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:d1f090196374399294138eba115b1d49cb39b64055da666dca60eeb76869ef3e
+oid sha256:06d8357937323927eea654ac28ecfd1b62aedcbfc6a39dac300abdf3432c838a
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71ef0ac4047cf918a26ef6bb15fb7a52f3223d00cba2a4a9275953afc3aea46a
+oid sha256:76d0de146784eeb26292d498175aa99311458e3aa89446d3583abb200fc9d4b5
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
+oid sha256:56e4c605570ee3c73fe8ff5167e52a53ea3100415d1bfd842431b5b9a62a411e
 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": 0.00045193484605969304,
+  "epoch": 0.0006779022690895396,
   "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": 384.992,
       "eval_steps_per_second": 192.496,
       "step": 6
+    },
+    {
+      "epoch": 0.0005272573204029753,
+      "grad_norm": 0.0817117989063263,
+      "learning_rate": 0.00014,
+      "loss": 10.3669,
+      "step": 7
+    },
+    {
+      "epoch": 0.0006025797947462574,
+      "grad_norm": 0.07650120556354523,
+      "learning_rate": 0.00016,
+      "loss": 10.3662,
+      "step": 8
+    },
+    {
+      "epoch": 0.0006779022690895396,
+      "grad_norm": 0.07249870896339417,
+      "learning_rate": 0.00018,
+      "loss": 10.3654,
+      "step": 9
+    },
+    {
+      "epoch": 0.0006779022690895396,
+      "eval_loss": 10.366414070129395,
+      "eval_runtime": 14.3772,
+      "eval_samples_per_second": 388.811,
+      "eval_steps_per_second": 194.406,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 77585448960.0,
+  "total_flos": 116378173440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null