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:d95501e2faf37a10f7cb7244f116d5a577a5f4513b331af0fba71fd09a3745e0
+oid sha256:2ca5cb65a0c8e41dd5840a249884f0a782952af47dbd3f265b29b20b9d8b2566
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7a9674e60a0ad3042fddf59880d19e9e2cbd62559bc2b394764b467f3fd6380
+oid sha256:143ee8a41179d4f9d6ccf1444b100a5f799c6768d739a8343243896814935414
 size 170920532

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17f8f9f4387f81b40a6eb494a35dbbd9471508cfba03a93ad0463a107021279f
+oid sha256:4e50df1ff4672c4a578ad9199d83d6e53829b74f0e3358db91be8155fd418448
 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": 2.2555510997772217,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.31452035645640397,
+  "best_metric": 2.206881284713745,
+  "best_model_checkpoint": "miner_id_24/checkpoint-600",
+  "epoch": 0.4193604752752053,
   "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": 13.578,
       "eval_steps_per_second": 3.397,
       "step": 450
+    },
+    {
+      "epoch": 0.32150969771099075,
+      "grad_norm": 6.887442111968994,
+      "learning_rate": 2.6522584913693294e-05,
+      "loss": 9.1238,
+      "step": 460
+    },
+    {
+      "epoch": 0.3284990389655775,
+      "grad_norm": 10.633115768432617,
+      "learning_rate": 2.301660165700936e-05,
+      "loss": 8.9099,
+      "step": 470
+    },
+    {
+      "epoch": 0.33548838022016425,
+      "grad_norm": 11.0469331741333,
+      "learning_rate": 1.9728836206903656e-05,
+      "loss": 8.8348,
+      "step": 480
+    },
+    {
+      "epoch": 0.34247772147475103,
+      "grad_norm": 11.225386619567871,
+      "learning_rate": 1.6668608091748495e-05,
+      "loss": 8.9982,
+      "step": 490
+    },
+    {
+      "epoch": 0.34946706272933775,
+      "grad_norm": 24.77507972717285,
+      "learning_rate": 1.3844591860619383e-05,
+      "loss": 9.5045,
+      "step": 500
+    },
+    {
+      "epoch": 0.34946706272933775,
+      "eval_loss": 2.2151849269866943,
+      "eval_runtime": 177.4559,
+      "eval_samples_per_second": 13.581,
+      "eval_steps_per_second": 3.398,
+      "step": 500
+    },
+    {
+      "epoch": 0.35645640398392453,
+      "grad_norm": 8.592710494995117,
+      "learning_rate": 1.1264792494342857e-05,
+      "loss": 8.9247,
+      "step": 510
+    },
+    {
+      "epoch": 0.36344574523851125,
+      "grad_norm": 10.218486785888672,
+      "learning_rate": 8.936522714508678e-06,
+      "loss": 8.7595,
+      "step": 520
+    },
+    {
+      "epoch": 0.37043508649309803,
+      "grad_norm": 13.771211624145508,
+      "learning_rate": 6.866382254766157e-06,
+      "loss": 8.7061,
+      "step": 530
+    },
+    {
+      "epoch": 0.37742442774768475,
+      "grad_norm": 12.511350631713867,
+      "learning_rate": 5.060239153161872e-06,
+      "loss": 8.9121,
+      "step": 540
+    },
+    {
+      "epoch": 0.38441376900227153,
+      "grad_norm": 19.870609283447266,
+      "learning_rate": 3.5232131185484076e-06,
+      "loss": 9.5899,
+      "step": 550
+    },
+    {
+      "epoch": 0.38441376900227153,
+      "eval_loss": 2.205038070678711,
+      "eval_runtime": 177.3353,
+      "eval_samples_per_second": 13.59,
+      "eval_steps_per_second": 3.4,
+      "step": 550
+    },
+    {
+      "epoch": 0.3914031102568583,
+      "grad_norm": 7.469477653503418,
+      "learning_rate": 2.259661018213333e-06,
+      "loss": 9.0318,
+      "step": 560
+    },
+    {
+      "epoch": 0.39839245151144503,
+      "grad_norm": 9.499835968017578,
+      "learning_rate": 1.2731645278655445e-06,
+      "loss": 8.7828,
+      "step": 570
+    },
+    {
+      "epoch": 0.4053817927660318,
+      "grad_norm": 14.364631652832031,
+      "learning_rate": 5.665199789862907e-07,
+      "loss": 8.7563,
+      "step": 580
+    },
+    {
+      "epoch": 0.41237113402061853,
+      "grad_norm": 12.063446998596191,
+      "learning_rate": 1.4173043232380557e-07,
+      "loss": 8.691,
+      "step": 590
+    },
+    {
+      "epoch": 0.4193604752752053,
+      "grad_norm": 20.08045768737793,
+      "learning_rate": 0.0,
+      "loss": 9.6758,
+      "step": 600
+    },
+    {
+      "epoch": 0.4193604752752053,
+      "eval_loss": 2.206881284713745,
+      "eval_runtime": 177.3758,
+      "eval_samples_per_second": 13.587,
+      "eval_steps_per_second": 3.4,
+      "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": 6.365274005569536e+17,
+  "total_flos": 8.487032007426048e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null