Training in progress, step 52, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfee01d8103d09d582705d572b496d7643cb63480e69b153f1382b5081aa8af8
+oid sha256:f1a1f7edba342dcae21bc1bcc931a8d18e8fcd5b7452808965c7181e3f8fb2f1
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec7a651830d44bcee6bff272d2302cedf7b43d75bfde70141fda080f96fb44f
+oid sha256:c31134d8c644da3fe4e7fe5335cea6c99d373c2c3f4bfc42b0a9f8a83ee3881e
 size 1001863522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d83117332e05dc7fd0876bf6486e3944c984131f2f9ab4cca3b30ddf4c26a56
+oid sha256:8e4f84759c0d0345e3d0ec8c8f48cc65de394faca774211b25c2f484b7ca4dbc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afb9c3c0c925ea8cf32a1dcba2e2f6242aaac5236534a8df451537dd590ac10a
+oid sha256:a0083f46b3c06809c7ba2e6389d4ff484bc53254e300d739b3ff127153f94c8d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5461706783369803,
+  "epoch": 0.7282275711159737,
   "eval_steps": 50,
-  "global_step": 39,
+  "global_step": 52,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -288,6 +288,105 @@
       "learning_rate": 0.00014223202029717776,
       "loss": 2.6442,
       "step": 39
+    },
+    {
+      "epoch": 0.5601750547045952,
+      "grad_norm": 7.39982271194458,
+      "learning_rate": 0.0001414092019239907,
+      "loss": 1.7663,
+      "step": 40
+    },
+    {
+      "epoch": 0.57417943107221,
+      "grad_norm": 8.183086395263672,
+      "learning_rate": 0.00014054760244698884,
+      "loss": 1.7819,
+      "step": 41
+    },
+    {
+      "epoch": 0.5881838074398249,
+      "grad_norm": 6.441479682922363,
+      "learning_rate": 0.00013964772501600368,
+      "loss": 1.7133,
+      "step": 42
+    },
+    {
+      "epoch": 0.6021881838074398,
+      "grad_norm": 11.74283504486084,
+      "learning_rate": 0.00013871009513411408,
+      "loss": 2.4207,
+      "step": 43
+    },
+    {
+      "epoch": 0.6161925601750547,
+      "grad_norm": 6.086061477661133,
+      "learning_rate": 0.00013773526035076698,
+      "loss": 1.271,
+      "step": 44
+    },
+    {
+      "epoch": 0.6301969365426696,
+      "grad_norm": 8.047619819641113,
+      "learning_rate": 0.00013672378994202423,
+      "loss": 1.837,
+      "step": 45
+    },
+    {
+      "epoch": 0.6442013129102845,
+      "grad_norm": 11.720404624938965,
+      "learning_rate": 0.00013567627457812106,
+      "loss": 1.9628,
+      "step": 46
+    },
+    {
+      "epoch": 0.6582056892778994,
+      "grad_norm": 7.418464660644531,
+      "learning_rate": 0.00013459332597853157,
+      "loss": 2.1906,
+      "step": 47
+    },
+    {
+      "epoch": 0.6722100656455142,
+      "grad_norm": 5.253023147583008,
+      "learning_rate": 0.00013347557655474167,
+      "loss": 1.2249,
+      "step": 48
+    },
+    {
+      "epoch": 0.6862144420131291,
+      "grad_norm": 6.372616291046143,
+      "learning_rate": 0.0001323236790409386,
+      "loss": 1.5337,
+      "step": 49
+    },
+    {
+      "epoch": 0.700218818380744,
+      "grad_norm": 6.444860458374023,
+      "learning_rate": 0.00013113830611283258,
+      "loss": 1.9269,
+      "step": 50
+    },
+    {
+      "epoch": 0.700218818380744,
+      "eval_loss": 0.06303766369819641,
+      "eval_runtime": 37.4056,
+      "eval_samples_per_second": 6.443,
+      "eval_steps_per_second": 3.235,
+      "step": 50
+    },
+    {
+      "epoch": 0.7142231947483588,
+      "grad_norm": 6.532812118530273,
+      "learning_rate": 0.00012992014999483302,
+      "loss": 1.7148,
+      "step": 51
+    },
+    {
+      "epoch": 0.7282275711159737,
+      "grad_norm": 5.408838748931885,
+      "learning_rate": 0.00012866992205580908,
+      "loss": 2.6251,
+      "step": 52
     }
   ],
   "logging_steps": 1,
@@ -307,7 +406,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.9802418233344e+17,
+  "total_flos": 5.3069890977792e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null