Training in progress, step 462, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6030cdfec156be32c0ce5ce5c733e922acd059040b45ccb4972e725954306c40
+oid sha256:e3d71f135aaf51849845b589a0599d3e3c87aa7bb1cbd6352df3fb636193a03b
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6abef001eb5046117ec6eee464e1792aa5acbda3c0d305591284db66b9017c9d
+oid sha256:dfe1fa92a7323db508573f5ba92831f8d0c60c3665cbbe91b3e18368afe5ddfe
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:601d3cd30158a5ec1e80bcf2fe124c9ff7d378ee828c7f46d1e57e335b5624be
+oid sha256:35955a38f305f08a71cf5a6aeede99e60dbfc9c66fbb6b89f8f788d949eaddfc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9507fdefdfac1d5dbc7a23a3aeb675b6dd3cc22a3762b7e85ff02a1c9c43105
+oid sha256:7b58b44a2d5024ddc12e64ead45d5d25c7fc985d9aaeb44c7bc3de9b8cf56f23
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3680781758957654,
+  "epoch": 1.504885993485342,
   "eval_steps": 42,
-  "global_step": 420,
+  "global_step": 462,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1075,6 +1075,112 @@
       "eval_samples_per_second": 23.301,
       "eval_steps_per_second": 5.859,
       "step": 420
+    },
+    {
+      "epoch": 1.3778501628664495,
+      "grad_norm": 2.6252212524414062,
+      "learning_rate": 5.9702234071631e-06,
+      "loss": 0.694,
+      "step": 423
+    },
+    {
+      "epoch": 1.3876221498371335,
+      "grad_norm": 2.314903497695923,
+      "learning_rate": 5.5226705990794155e-06,
+      "loss": 0.7619,
+      "step": 426
+    },
+    {
+      "epoch": 1.3973941368078175,
+      "grad_norm": 2.5821728706359863,
+      "learning_rate": 5.091571939329048e-06,
+      "loss": 0.8219,
+      "step": 429
+    },
+    {
+      "epoch": 1.4071661237785016,
+      "grad_norm": 2.4021191596984863,
+      "learning_rate": 4.677086910538092e-06,
+      "loss": 0.6944,
+      "step": 432
+    },
+    {
+      "epoch": 1.4169381107491856,
+      "grad_norm": 2.5493106842041016,
+      "learning_rate": 4.279368849209381e-06,
+      "loss": 0.7945,
+      "step": 435
+    },
+    {
+      "epoch": 1.4267100977198697,
+      "grad_norm": 2.4301791191101074,
+      "learning_rate": 3.898564888996476e-06,
+      "loss": 0.6487,
+      "step": 438
+    },
+    {
+      "epoch": 1.4364820846905537,
+      "grad_norm": 2.63675856590271,
+      "learning_rate": 3.534815906272404e-06,
+      "loss": 0.8646,
+      "step": 441
+    },
+    {
+      "epoch": 1.4462540716612378,
+      "grad_norm": 2.5258288383483887,
+      "learning_rate": 3.18825646801314e-06,
+      "loss": 0.7682,
+      "step": 444
+    },
+    {
+      "epoch": 1.4560260586319218,
+      "grad_norm": 2.3839597702026367,
+      "learning_rate": 2.8590147820153513e-06,
+      "loss": 0.8041,
+      "step": 447
+    },
+    {
+      "epoch": 1.4657980456026058,
+      "grad_norm": 2.62052583694458,
+      "learning_rate": 2.547212649466568e-06,
+      "loss": 0.806,
+      "step": 450
+    },
+    {
+      "epoch": 1.47557003257329,
+      "grad_norm": 2.2883756160736084,
+      "learning_rate": 2.2529654198854835e-06,
+      "loss": 0.7404,
+      "step": 453
+    },
+    {
+      "epoch": 1.485342019543974,
+      "grad_norm": 2.6609508991241455,
+      "learning_rate": 1.9763819484490355e-06,
+      "loss": 0.7702,
+      "step": 456
+    },
+    {
+      "epoch": 1.495114006514658,
+      "grad_norm": 2.525723695755005,
+      "learning_rate": 1.7175645557220566e-06,
+      "loss": 0.769,
+      "step": 459
+    },
+    {
+      "epoch": 1.504885993485342,
+      "grad_norm": 2.766369581222534,
+      "learning_rate": 1.4766089898042678e-06,
+      "loss": 0.7819,
+      "step": 462
+    },
+    {
+      "epoch": 1.504885993485342,
+      "eval_loss": 1.304705262184143,
+      "eval_runtime": 22.2456,
+      "eval_samples_per_second": 23.241,
+      "eval_steps_per_second": 5.844,
+      "step": 462
     }
   ],
   "logging_steps": 3,
@@ -1094,7 +1200,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.1674071048729395e+17,
+  "total_flos": 3.484194956409569e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null