Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca969bac8c3a51ce101a875a6ff3bf9663ace1b1f9f3e5328bfdfb3c2d0edd32
+oid sha256:ee622886776cc2a74eddd2257adb3c14327210894b43355dad2777819786e3f2
 size 66103768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a405201cdeb62094096555859e2ba15c821cbe5e404d3ac097338175e4c4ac19
+oid sha256:3fd90aff9c3cb8c82a6da351b9405ed0e5432e79da49061eac3f6b19ed3a8baf
 size 33939412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1b8dbc95226369ce8d50542a4f2958de0c5011de7538e300ac07fb3e667e6c2
+oid sha256:00f7b12f69d3b05044a3955f6c478cb95db87dc0c1f03f25c891c981855ed0b5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01704731723308928,
+  "epoch": 0.021855534914217024,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 15.232,
       "eval_steps_per_second": 7.616,
       "step": 39
+    },
+    {
+      "epoch": 0.01748442793137362,
+      "grad_norm": 1.740352749824524,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 9.5432,
+      "step": 40
+    },
+    {
+      "epoch": 0.017921538629657962,
+      "grad_norm": 1.7021613121032715,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 9.3533,
+      "step": 41
+    },
+    {
+      "epoch": 0.018358649327942303,
+      "grad_norm": 1.6590347290039062,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 9.7998,
+      "step": 42
+    },
+    {
+      "epoch": 0.01879576002622664,
+      "grad_norm": 1.6528631448745728,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 9.4514,
+      "step": 43
+    },
+    {
+      "epoch": 0.01923287072451098,
+      "grad_norm": 1.6342215538024902,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 8.8211,
+      "step": 44
+    },
+    {
+      "epoch": 0.019669981422795323,
+      "grad_norm": 1.6100610494613647,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 8.5215,
+      "step": 45
+    },
+    {
+      "epoch": 0.020107092121079664,
+      "grad_norm": 1.6995798349380493,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 10.238,
+      "step": 46
+    },
+    {
+      "epoch": 0.020544202819364005,
+      "grad_norm": 1.6126399040222168,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 8.8309,
+      "step": 47
+    },
+    {
+      "epoch": 0.020981313517648346,
+      "grad_norm": 1.634695291519165,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 9.3769,
+      "step": 48
+    },
+    {
+      "epoch": 0.021418424215932683,
+      "grad_norm": 1.7255252599716187,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 8.8856,
+      "step": 49
+    },
+    {
+      "epoch": 0.021855534914217024,
+      "grad_norm": 1.6557931900024414,
+      "learning_rate": 0.0,
+      "loss": 9.1025,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.1235045141725184e+16,
+  "total_flos": 1.44039040278528e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null