Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9728d9ea717659640b33eac820e8f2635cee3b307ef358a0ff4945f21e9ceee
+oid sha256:c6a9215a28ac872da52f55aa19af9b4ee906373701fc6e5b55f68e973faffe57
 size 339512200

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b96feeb44097cd300a1f7d72f7938fb3ab57e54288c1f21baff0c575f25a963
+oid sha256:05ad7d0fbd10afe05f5e34de56623ac3ae28854fd1e0a22f3a69eb3d6bbd6439
 size 659562874

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cab2295487651294553c4caf49c38f12ef02ee011d6e686596a41aeb1665f09
+oid sha256:176b20eb86b16b21531afeae0fcad43474b9a44ba3c085cf5ebf304a89fb5f43
 size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40989f422992086de56b7ab56f6bba81cac547e6785f52be59f14989b370dd0e
+oid sha256:80737f34367bed0f31ec1eeecad8be2c3717a20421ad2a8f693a5747cb780b5c
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7156569361686707,
   "best_model_checkpoint": "./output/checkpoint-300",
-  "epoch": 3.3333333333333335,
+  "epoch": 3.8095238095238093,
   "eval_steps": 150,
-  "global_step": 1050,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -798,6 +798,119 @@
       "eval_samples_per_second": 13.193,
       "eval_steps_per_second": 13.193,
       "step": 1050
+    },
+    {
+      "epoch": 3.365079365079365,
+      "grad_norm": 4.088830947875977,
+      "learning_rate": 9.082436730845992e-05,
+      "loss": 0.2478,
+      "step": 1060
+    },
+    {
+      "epoch": 3.3968253968253967,
+      "grad_norm": 3.7507574558258057,
+      "learning_rate": 9.063844375723012e-05,
+      "loss": 0.1793,
+      "step": 1070
+    },
+    {
+      "epoch": 3.4285714285714284,
+      "grad_norm": 4.122824668884277,
+      "learning_rate": 9.045084971874735e-05,
+      "loss": 0.2135,
+      "step": 1080
+    },
+    {
+      "epoch": 3.4603174603174605,
+      "grad_norm": 8.127439498901367,
+      "learning_rate": 9.026159290426779e-05,
+      "loss": 0.1958,
+      "step": 1090
+    },
+    {
+      "epoch": 3.492063492063492,
+      "grad_norm": 3.515589952468872,
+      "learning_rate": 9.007068109339781e-05,
+      "loss": 0.184,
+      "step": 1100
+    },
+    {
+      "epoch": 3.5238095238095237,
+      "grad_norm": 4.518334865570068,
+      "learning_rate": 8.987812213377421e-05,
+      "loss": 0.2064,
+      "step": 1110
+    },
+    {
+      "epoch": 3.5555555555555554,
+      "grad_norm": 3.4224295616149902,
+      "learning_rate": 8.968392394074161e-05,
+      "loss": 0.1771,
+      "step": 1120
+    },
+    {
+      "epoch": 3.5873015873015874,
+      "grad_norm": 5.875314235687256,
+      "learning_rate": 8.94880944970271e-05,
+      "loss": 0.3107,
+      "step": 1130
+    },
+    {
+      "epoch": 3.619047619047619,
+      "grad_norm": 6.066832065582275,
+      "learning_rate": 8.92906418524121e-05,
+      "loss": 0.2793,
+      "step": 1140
+    },
+    {
+      "epoch": 3.6507936507936507,
+      "grad_norm": 0.021297266706824303,
+      "learning_rate": 8.909157412340148e-05,
+      "loss": 0.2369,
+      "step": 1150
+    },
+    {
+      "epoch": 3.682539682539683,
+      "grad_norm": 8.33176040649414,
+      "learning_rate": 8.889089949288984e-05,
+      "loss": 0.2405,
+      "step": 1160
+    },
+    {
+      "epoch": 3.7142857142857144,
+      "grad_norm": 4.250291347503662,
+      "learning_rate": 8.868862620982532e-05,
+      "loss": 0.1879,
+      "step": 1170
+    },
+    {
+      "epoch": 3.746031746031746,
+      "grad_norm": 7.068946361541748,
+      "learning_rate": 8.848476258887028e-05,
+      "loss": 0.2618,
+      "step": 1180
+    },
+    {
+      "epoch": 3.7777777777777777,
+      "grad_norm": 7.198329448699951,
+      "learning_rate": 8.827931701005971e-05,
+      "loss": 0.2264,
+      "step": 1190
+    },
+    {
+      "epoch": 3.8095238095238093,
+      "grad_norm": 8.922143936157227,
+      "learning_rate": 8.80722979184567e-05,
+      "loss": 0.3599,
+      "step": 1200
+    },
+    {
+      "epoch": 3.8095238095238093,
+      "eval_loss": 0.8716204762458801,
+      "eval_runtime": 21.3108,
+      "eval_samples_per_second": 13.139,
+      "eval_steps_per_second": 13.139,
+      "step": 1200
     }
   ],
   "logging_steps": 10,
@@ -817,7 +930,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.199995203854336e+16,
+  "total_flos": 2.511073958137037e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null