Training in progress, step 4800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4680c74d3e74636d523589cf6c88c19b1f0b27a85c02d77aa3b2ab43ae2c326b
+oid sha256:4011e09ddfae4e3a1ffe58646f199bd06fe4a378448a2620cd0a4b4033fe0401
 size 977382808

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4097e2b0a796bf348b26a31428ff0f4fde61130effb28c70c130def103553f2
+oid sha256:4cf83288afd34e01dbde4d77616a9ed0057f110bb380543e04e5b7ac4db7f75d
 size 1933063674

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56fbd2a88a45e10e2cc4bc3b7d5dded63a8c2bb556c749244d2e63aac853f9e3
+oid sha256:a1c08b9ac5cae29dc81399edbb4b85e4bd0896ca8b9aa0441d3c88764d2f23a8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5aa7843fee19f986423b7658b656356c03da99a77a7d470397314a84a80a47a
+oid sha256:536269e746606d89d7092eefc1d242400387136c0a490c65f4003318a00e54ce
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.40145647525787354,
-  "best_model_checkpoint": "./output/checkpoint-4650",
-  "epoch": 0.3772819472616633,
+  "best_metric": 0.40103402733802795,
+  "best_model_checkpoint": "./output/checkpoint-4800",
+  "epoch": 0.3894523326572008,
   "eval_steps": 150,
-  "global_step": 4650,
+  "global_step": 4800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3510,6 +3510,119 @@
       "eval_samples_per_second": 6.797,
       "eval_steps_per_second": 6.797,
       "step": 4650
+    },
+    {
+      "epoch": 0.37809330628803245,
+      "grad_norm": 1.5403624773025513,
+      "learning_rate": 9.466184635518361e-07,
+      "loss": 0.4279,
+      "step": 4660
+    },
+    {
+      "epoch": 0.37890466531440165,
+      "grad_norm": 1.6227903366088867,
+      "learning_rate": 8.919587459299461e-07,
+      "loss": 0.3913,
+      "step": 4670
+    },
+    {
+      "epoch": 0.3797160243407708,
+      "grad_norm": 2.332197427749634,
+      "learning_rate": 8.389066067082852e-07,
+      "loss": 0.371,
+      "step": 4680
+    },
+    {
+      "epoch": 0.38052738336714,
+      "grad_norm": 1.9335829019546509,
+      "learning_rate": 7.874642266525102e-07,
+      "loss": 0.4271,
+      "step": 4690
+    },
+    {
+      "epoch": 0.3813387423935091,
+      "grad_norm": 2.0961616039276123,
+      "learning_rate": 7.376337203573824e-07,
+      "loss": 0.3793,
+      "step": 4700
+    },
+    {
+      "epoch": 0.3821501014198783,
+      "grad_norm": 2.0990850925445557,
+      "learning_rate": 6.894171361598467e-07,
+      "loss": 0.3498,
+      "step": 4710
+    },
+    {
+      "epoch": 0.38296146044624746,
+      "grad_norm": 1.7860051393508911,
+      "learning_rate": 6.428164560548134e-07,
+      "loss": 0.385,
+      "step": 4720
+    },
+    {
+      "epoch": 0.38377281947261666,
+      "grad_norm": 1.7000079154968262,
+      "learning_rate": 5.978335956137304e-07,
+      "loss": 0.3687,
+      "step": 4730
+    },
+    {
+      "epoch": 0.3845841784989858,
+      "grad_norm": 1.7352828979492188,
+      "learning_rate": 5.544704039058025e-07,
+      "loss": 0.3936,
+      "step": 4740
+    },
+    {
+      "epoch": 0.385395537525355,
+      "grad_norm": 1.6553871631622314,
+      "learning_rate": 5.12728663421993e-07,
+      "loss": 0.3656,
+      "step": 4750
+    },
+    {
+      "epoch": 0.38620689655172413,
+      "grad_norm": 1.4046574831008911,
+      "learning_rate": 4.7261009000177274e-07,
+      "loss": 0.3642,
+      "step": 4760
+    },
+    {
+      "epoch": 0.38701825557809333,
+      "grad_norm": 1.7016775608062744,
+      "learning_rate": 4.3411633276255307e-07,
+      "loss": 0.4031,
+      "step": 4770
+    },
+    {
+      "epoch": 0.38782961460446247,
+      "grad_norm": 1.5665788650512695,
+      "learning_rate": 3.972489740319274e-07,
+      "loss": 0.3766,
+      "step": 4780
+    },
+    {
+      "epoch": 0.38864097363083167,
+      "grad_norm": 1.9446560144424438,
+      "learning_rate": 3.62009529282612e-07,
+      "loss": 0.418,
+      "step": 4790
+    },
+    {
+      "epoch": 0.3894523326572008,
+      "grad_norm": 1.5468990802764893,
+      "learning_rate": 3.283994470701579e-07,
+      "loss": 0.3958,
+      "step": 4800
+    },
+    {
+      "epoch": 0.3894523326572008,
+      "eval_loss": 0.40103402733802795,
+      "eval_runtime": 73.6918,
+      "eval_samples_per_second": 6.785,
+      "eval_steps_per_second": 6.785,
+      "step": 4800
     }
   ],
   "logging_steps": 10,
@@ -3529,7 +3642,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.122448205028475e+17,
+  "total_flos": 9.407167035923005e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null