Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fda06ab3b9da88da90f8525aac66f70967327d6feeba7c87753bb6fd2a3c06a
+oid sha256:ff1f1c7995d36156a8be4e4e3781a3de815fedc7dbabc2f3f2000eb44db968ea
 size 63592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d86a3bdbbf879ea83179ce784f3802978823b28b27b70ad7c8614c2d944ccda6
+oid sha256:628e9f3b165ddd57f211900f0fad27047990e84538320468266f0237d48e8ad7
 size 132798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e6185ad6ed959cd39fa8d11c56d0794242896a9c8e345712df8715d9227105b
+oid sha256:130a4817f279520af77199dd42cfe37117aa5a80f4f47a83e4ce4ffd703225e8
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb18989b9381f7e1d91acca88837ecfcbbb4471192e2d82c3f0fef20a6f55328
+oid sha256:5ce832b0bc79ceb292a621d3a04b07c47bedaaa273036406343d169de473543a
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a69df2de80e994e32a0ab6d23608ed1055a6daf2045217ffa630692204364929
+oid sha256:7eb4792b082408543f1f81b7312692c86c5c6fa9529cb1cb2974620aef9db475
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62279f496f576747a2394a22086176d8b2e0862deae431c1947e811cf4f7e2f1
+oid sha256:081b82e0dcfc94fe383b962c8243795f817dd269c3e9a8642c2270f1b678e5d3
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:034267d82a487bb38b948011560fd8e07c148e8da754832aa457357ec1cc8c11
+oid sha256:e6fceeedbf4260961cb70678e67afb103efe4228c70593decfaea3fc69afbdcb
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb8e12e7aed703decfb3f1bd196e7dac87103db27d85576282f7717cff7108ae
+oid sha256:806fdff23908b2cb3eaf085ea29ccebb1c2764e61ea98e5f46b30864a683a45c
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe4583d5c1e73d7f7fc7cf22c5b5278a33e65b7a63b4f56c19aafa977ef64bc5
+oid sha256:2eb4ac8e97914a207a71ff5f3ba208f868ef5f748830c0fc4f7cfca000796510
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2071e0645e19af246f30b3894b4ee75eca183e708cbe6a8dfbdad202ff8b9cf
+oid sha256:7710803b72c4a46e34d6599dca7b70dd6d7b92a90af6e926e9a1a9da54b9ece3
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0029498525073746312,
+  "epoch": 0.004424778761061947,
   "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": 687.866,
       "eval_steps_per_second": 86.134,
       "step": 6
+    },
+    {
+      "epoch": 0.00344149459193707,
+      "grad_norm": 9.985726356506348,
+      "learning_rate": 8e-05,
+      "loss": 44.3643,
+      "step": 7
+    },
+    {
+      "epoch": 0.003933136676499509,
+      "grad_norm": 9.569968223571777,
+      "learning_rate": 0.0001,
+      "loss": 44.3188,
+      "step": 8
+    },
+    {
+      "epoch": 0.004424778761061947,
+      "grad_norm": 8.405980110168457,
+      "learning_rate": 0.00012,
+      "loss": 44.2661,
+      "step": 9
+    },
+    {
+      "epoch": 0.004424778761061947,
+      "eval_loss": 11.050333976745605,
+      "eval_runtime": 5.0102,
+      "eval_samples_per_second": 683.801,
+      "eval_steps_per_second": 85.625,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 179683983360.0,
+  "total_flos": 269525975040.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null