Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6332954eced366f37dfa0feeafda882ef0b7137fc497129122aa90280c207e12
+oid sha256:7c6db9a1befbdf96a10eb4549f5c11bb62b71c871fc1449a4ceb1d04e854c30a
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c451d16ef10ec74b175dfb29380c22e605ba1df9ea11b88d2ccb1b29333371d
+oid sha256:c66c42c906aa76007f6b840d28d3671397c29fafb8ec2a00a943aefb2881f063
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:934ae21caf3ad57aad1e085732f92e778c42e733d2e77db72cee584a6cee29f1
+oid sha256:3bf8fd01cb1f6f9e37877eae1b37636fde2b75f869af10bcba05747b44361cb5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bd00e418debe68a52c354ffbeb17299ae0b053a4079b4b4c3f7c38706aea24d
+oid sha256:d701c4e4bcddd7438a47fc5bf2bf52cf308baa5fb5488432aa3ee78319007661
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.2125701606273651,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-1000",
-  "epoch": 0.7024938531787847,
+  "best_metric": 0.20940540730953217,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-1500",
+  "epoch": 1.053740779768177,
   "eval_steps": 100,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -227,6 +227,116 @@
       "eval_samples_per_second": 66.047,
       "eval_steps_per_second": 2.073,
       "step": 1000
+    },
+    {
+      "epoch": 0.7376185458377239,
+      "grad_norm": 26256.35546875,
+      "learning_rate": 2.4465917076598737e-05,
+      "loss": 0.2224,
+      "step": 1050
+    },
+    {
+      "epoch": 0.7727432384966632,
+      "grad_norm": 29107.78515625,
+      "learning_rate": 2.420238931834153e-05,
+      "loss": 0.2211,
+      "step": 1100
+    },
+    {
+      "epoch": 0.7727432384966632,
+      "eval_loss": 0.2117428034543991,
+      "eval_runtime": 67.5369,
+      "eval_samples_per_second": 66.038,
+      "eval_steps_per_second": 2.073,
+      "step": 1100
+    },
+    {
+      "epoch": 0.8078679311556024,
+      "grad_norm": 98354.15625,
+      "learning_rate": 2.393886156008433e-05,
+      "loss": 0.215,
+      "step": 1150
+    },
+    {
+      "epoch": 0.8429926238145417,
+      "grad_norm": 22886.3984375,
+      "learning_rate": 2.3675333801827128e-05,
+      "loss": 0.2229,
+      "step": 1200
+    },
+    {
+      "epoch": 0.8429926238145417,
+      "eval_loss": 0.2107735425233841,
+      "eval_runtime": 67.6295,
+      "eval_samples_per_second": 65.948,
+      "eval_steps_per_second": 2.07,
+      "step": 1200
+    },
+    {
+      "epoch": 0.8781173164734809,
+      "grad_norm": 20510.26171875,
+      "learning_rate": 2.3411806043569923e-05,
+      "loss": 0.2105,
+      "step": 1250
+    },
+    {
+      "epoch": 0.91324200913242,
+      "grad_norm": 20053.85546875,
+      "learning_rate": 2.314827828531272e-05,
+      "loss": 0.2195,
+      "step": 1300
+    },
+    {
+      "epoch": 0.91324200913242,
+      "eval_loss": 0.20966531336307526,
+      "eval_runtime": 67.6112,
+      "eval_samples_per_second": 65.965,
+      "eval_steps_per_second": 2.071,
+      "step": 1300
+    },
+    {
+      "epoch": 0.9483667017913593,
+      "grad_norm": 28154.595703125,
+      "learning_rate": 2.2884750527055516e-05,
+      "loss": 0.2215,
+      "step": 1350
+    },
+    {
+      "epoch": 0.9834913944502985,
+      "grad_norm": 28011.71484375,
+      "learning_rate": 2.2621222768798314e-05,
+      "loss": 0.2172,
+      "step": 1400
+    },
+    {
+      "epoch": 0.9834913944502985,
+      "eval_loss": 0.20960816740989685,
+      "eval_runtime": 67.6089,
+      "eval_samples_per_second": 65.968,
+      "eval_steps_per_second": 2.071,
+      "step": 1400
+    },
+    {
+      "epoch": 1.0186160871092378,
+      "grad_norm": 26518.01171875,
+      "learning_rate": 2.2357695010541112e-05,
+      "loss": 0.21,
+      "step": 1450
+    },
+    {
+      "epoch": 1.053740779768177,
+      "grad_norm": 20411.26171875,
+      "learning_rate": 2.2094167252283907e-05,
+      "loss": 0.2139,
+      "step": 1500
+    },
+    {
+      "epoch": 1.053740779768177,
+      "eval_loss": 0.20940540730953217,
+      "eval_runtime": 67.4684,
+      "eval_samples_per_second": 66.105,
+      "eval_steps_per_second": 2.075,
+      "step": 1500
     }
   ],
   "logging_steps": 50,
@@ -246,7 +356,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9743326248960000.0,
+  "total_flos": 1.46127057813504e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null