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:fee81af08f869f5a2c34eabb4c34c2abf96c685acefcbdadabb18d56e1e6970b
+oid sha256:24b984f0adf252057f8a548186929e1bbaea041a474450fd99ea020dbce5509f
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a949f718c77ec182a9ccd13d87c1cde37c514936590a08bb3e0f6258c74a4d8
+oid sha256:9bb192c0eccab3aeb6a94dc9aa18e42b51b805ac86f785afd216f5d76470132d
 size 51244020

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:542dca4f4c2f4ea912f1b02e1fbd6839b42d4b1d7135f3519e0443bfb2f1698f
+oid sha256:40ea77f018796dcf8ae76f21379caa245d6284be42f91ddb9f79d052af222a09
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82753beea79d6eaa1bbe3ad074629d37591cc09b8d77714e57f18e54d7536c59
+oid sha256:52a46a85e9822a83f7056a66ce5cf602266c078604815d20179f1946b51adceb
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:283338c6301e3bea91766d4cd295197613c18b7552eb5b2cdd8eb3e1f7284015
+oid sha256:7499df1e2b20e2bb9ca96b738f88bf92d10eade62a32613ebf1ba9483a67d8a6
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f866350560f1a9ff1a0bb594631bef91082ae127cf474a6568fd389519cf8a4a
+oid sha256:816fd80ed6a88c86b5af4f882f2f1da364df6e8adfb262c3dda8840495f52257
 size 15024

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": 0.01927710843373494,
+  "epoch": 0.02891566265060241,
   "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": 84.26,
       "eval_steps_per_second": 10.613,
       "step": 6
+    },
+    {
+      "epoch": 0.02248995983935743,
+      "grad_norm": 7.49973201751709,
+      "learning_rate": 0.00014,
+      "loss": 2.8421,
+      "step": 7
+    },
+    {
+      "epoch": 0.02570281124497992,
+      "grad_norm": 7.562386512756348,
+      "learning_rate": 0.00016,
+      "loss": 2.1444,
+      "step": 8
+    },
+    {
+      "epoch": 0.02891566265060241,
+      "grad_norm": 6.556207180023193,
+      "learning_rate": 0.00018,
+      "loss": 1.8961,
+      "step": 9
+    },
+    {
+      "epoch": 0.02891566265060241,
+      "eval_loss": 2.141901731491089,
+      "eval_runtime": 6.22,
+      "eval_samples_per_second": 84.244,
+      "eval_steps_per_second": 10.611,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5064392030814208.0,
+  "total_flos": 7453256196292608.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null