Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b2d074aab499d9f80bddf337d0040a5830648d9c389b9b8224fac118d49e0c3
+oid sha256:abd300e617c4644581e134cbb3f0defa2e232bd9e38c02fdba3e6fdf407ce8d4
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4160a0bc908544956e44c09f66a7a1476e98b135bf884d5322db7950786f491c
+oid sha256:5879fbdc8549eda7dd027d6776748a66495e39b712b6f9da60a140ece8bf090d
 size 51613668

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:816123bdea76b0b8211255a74e4532d61283c516b9776b7a83d70742a8c3b82c
+oid sha256:527ec3a62a42ec7f863679e8bf0970102aa27708dc9b1b018d3bc5b9da4120fb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70f0f789b56065211b8c0b1a5e2a97dd0b5b08a816bbbe288fb6f9c677282af9
+oid sha256:5ad54995b081fae25638228c5d9c8f38ca277e5c5ad00bc3e49897b543f84405
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.169210910797119,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.0464025160475368,
+  "best_metric": 2.157806873321533,
+  "best_model_checkpoint": "miner_id_24/checkpoint-600",
+  "epoch": 0.061870021396715734,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,135 @@
       "eval_samples_per_second": 48.948,
       "eval_steps_per_second": 12.238,
       "step": 450
+    },
+    {
+      "epoch": 0.04743368307081539,
+      "grad_norm": 0.5070022344589233,
+      "learning_rate": 2.6522584913693294e-05,
+      "loss": 1.7542,
+      "step": 460
+    },
+    {
+      "epoch": 0.04846485009409399,
+      "grad_norm": 1.1527154445648193,
+      "learning_rate": 2.301660165700936e-05,
+      "loss": 2.0654,
+      "step": 470
+    },
+    {
+      "epoch": 0.04949601711737259,
+      "grad_norm": 1.4834057092666626,
+      "learning_rate": 1.9728836206903656e-05,
+      "loss": 2.6073,
+      "step": 480
+    },
+    {
+      "epoch": 0.05052718414065118,
+      "grad_norm": 2.081821918487549,
+      "learning_rate": 1.6668608091748495e-05,
+      "loss": 2.1154,
+      "step": 490
+    },
+    {
+      "epoch": 0.051558351163929775,
+      "grad_norm": 3.67146372795105,
+      "learning_rate": 1.3844591860619383e-05,
+      "loss": 2.0505,
+      "step": 500
+    },
+    {
+      "epoch": 0.051558351163929775,
+      "eval_loss": 2.1617953777313232,
+      "eval_runtime": 333.6758,
+      "eval_samples_per_second": 48.952,
+      "eval_steps_per_second": 12.239,
+      "step": 500
+    },
+    {
+      "epoch": 0.052589518187208376,
+      "grad_norm": 0.5439073443412781,
+      "learning_rate": 1.1264792494342857e-05,
+      "loss": 1.7707,
+      "step": 510
+    },
+    {
+      "epoch": 0.05362068521048697,
+      "grad_norm": 1.2288672924041748,
+      "learning_rate": 8.936522714508678e-06,
+      "loss": 2.105,
+      "step": 520
+    },
+    {
+      "epoch": 0.05465185223376556,
+      "grad_norm": 1.4869736433029175,
+      "learning_rate": 6.866382254766157e-06,
+      "loss": 2.59,
+      "step": 530
+    },
+    {
+      "epoch": 0.05568301925704416,
+      "grad_norm": 2.162022590637207,
+      "learning_rate": 5.060239153161872e-06,
+      "loss": 2.1897,
+      "step": 540
+    },
+    {
+      "epoch": 0.05671418628032276,
+      "grad_norm": 3.499267578125,
+      "learning_rate": 3.5232131185484076e-06,
+      "loss": 2.0738,
+      "step": 550
+    },
+    {
+      "epoch": 0.05671418628032276,
+      "eval_loss": 2.159189462661743,
+      "eval_runtime": 334.2901,
+      "eval_samples_per_second": 48.862,
+      "eval_steps_per_second": 12.217,
+      "step": 550
+    },
+    {
+      "epoch": 0.05774535330360135,
+      "grad_norm": 0.5425857901573181,
+      "learning_rate": 2.259661018213333e-06,
+      "loss": 1.7283,
+      "step": 560
+    },
+    {
+      "epoch": 0.058776520326879945,
+      "grad_norm": 1.2724061012268066,
+      "learning_rate": 1.2731645278655445e-06,
+      "loss": 2.0625,
+      "step": 570
+    },
+    {
+      "epoch": 0.05980768735015854,
+      "grad_norm": 1.4536103010177612,
+      "learning_rate": 5.665199789862907e-07,
+      "loss": 2.5846,
+      "step": 580
+    },
+    {
+      "epoch": 0.06083885437343714,
+      "grad_norm": 1.7772146463394165,
+      "learning_rate": 1.4173043232380557e-07,
+      "loss": 2.2722,
+      "step": 590
+    },
+    {
+      "epoch": 0.061870021396715734,
+      "grad_norm": 3.680924415588379,
+      "learning_rate": 0.0,
+      "loss": 2.0972,
+      "step": 600
+    },
+    {
+      "epoch": 0.061870021396715734,
+      "eval_loss": 2.157806873321533,
+      "eval_runtime": 333.7888,
+      "eval_samples_per_second": 48.935,
+      "eval_steps_per_second": 12.235,
+      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -425,12 +554,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9.42281408297042e+16,
+  "total_flos": 1.2563752110627226e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null