Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b41d75f016eac0ae6028c69a56cb10b00bc0b0c739d903c8f4aae0e1b581a08
+oid sha256:6775be95ff6980a99418358c7301e9d3da289b032a55589c9aa287dc2eb67f21
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1f83d43d1e5ba07ac883a5f7b7a67f8176e3e60d664c041178d864ea6a32324
+oid sha256:7211071fd6e5621f52f7c259efe20437282b9a26a83960b3ea4bc9860b2fc502
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3c6816a3db4c0b0e26d2476c5ad0649b6b92cc5d0ac7fcc1954d606c46e1bc3
+oid sha256:42bae7d33f7aff9fb12d2f56afc7b7d72ccf14ff954254c006be4089696df391
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba34bf7a4768f5122b3d7fac76f5d3bf20a25042949bcaaad604430a3ce0871f
+oid sha256:b78fee8e52286a36068a1e2a9477a94eee30dbff3275043e5b9fe3b9910e20a4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0768ad295417e43a65f211c9e307b0a6510f0845e35e0bb9d345fd7c06f0727c
+oid sha256:e282f05c6cd6707f33e3b78a72416751db65d2fdbebee5c62afa5e7a342efb47
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31932a761feb39583051c63e435731ed7a8918f5af2171006b065c1d5a32fc5a
+oid sha256:ed464d69419de6b8a93875c2bd483d8a996e2c246d0762b281d075994672fdd0
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.51509952545166,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.07817080320500293,
+  "best_metric": 2.43630313873291,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.15634160641000586,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 24.966,
       "eval_steps_per_second": 6.491,
       "step": 25
+    },
+    {
+      "epoch": 0.08129763533320306,
+      "grad_norm": 2.5973637104034424,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.3456,
+      "step": 26
+    },
+    {
+      "epoch": 0.08442446746140317,
+      "grad_norm": 2.757310390472412,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.3969,
+      "step": 27
+    },
+    {
+      "epoch": 0.08755129958960328,
+      "grad_norm": 3.2795515060424805,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.4594,
+      "step": 28
+    },
+    {
+      "epoch": 0.0906781317178034,
+      "grad_norm": 2.4924538135528564,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.4313,
+      "step": 29
+    },
+    {
+      "epoch": 0.09380496384600352,
+      "grad_norm": 2.260542154312134,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.3361,
+      "step": 30
+    },
+    {
+      "epoch": 0.09693179597420364,
+      "grad_norm": 1.74604332447052,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.2974,
+      "step": 31
+    },
+    {
+      "epoch": 0.10005862810240375,
+      "grad_norm": 1.271629810333252,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.2899,
+      "step": 32
+    },
+    {
+      "epoch": 0.10318546023060388,
+      "grad_norm": 1.225449562072754,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.3584,
+      "step": 33
+    },
+    {
+      "epoch": 0.10631229235880399,
+      "grad_norm": 1.117197036743164,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.3665,
+      "step": 34
+    },
+    {
+      "epoch": 0.1094391244870041,
+      "grad_norm": 1.334246039390564,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.4026,
+      "step": 35
+    },
+    {
+      "epoch": 0.11256595661520422,
+      "grad_norm": 1.4346826076507568,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.4023,
+      "step": 36
+    },
+    {
+      "epoch": 0.11569278874340434,
+      "grad_norm": 2.0627875328063965,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 2.7722,
+      "step": 37
+    },
+    {
+      "epoch": 0.11881962087160446,
+      "grad_norm": 0.9819260239601135,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.4724,
+      "step": 38
+    },
+    {
+      "epoch": 0.12194645299980457,
+      "grad_norm": 0.9288238286972046,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.2767,
+      "step": 39
+    },
+    {
+      "epoch": 0.1250732851280047,
+      "grad_norm": 0.9036171436309814,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.2425,
+      "step": 40
+    },
+    {
+      "epoch": 0.1282001172562048,
+      "grad_norm": 0.9765707850456238,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.2438,
+      "step": 41
+    },
+    {
+      "epoch": 0.13132694938440492,
+      "grad_norm": 0.8984200954437256,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.2662,
+      "step": 42
+    },
+    {
+      "epoch": 0.13445378151260504,
+      "grad_norm": 1.0145357847213745,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.3001,
+      "step": 43
+    },
+    {
+      "epoch": 0.13758061364080515,
+      "grad_norm": 1.061907172203064,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.2892,
+      "step": 44
+    },
+    {
+      "epoch": 0.14070744576900526,
+      "grad_norm": 1.0922386646270752,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.2792,
+      "step": 45
+    },
+    {
+      "epoch": 0.1438342778972054,
+      "grad_norm": 1.1090540885925293,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.2617,
+      "step": 46
+    },
+    {
+      "epoch": 0.14696111002540552,
+      "grad_norm": 1.2806262969970703,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.3924,
+      "step": 47
+    },
+    {
+      "epoch": 0.15008794215360563,
+      "grad_norm": 1.502442479133606,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.4509,
+      "step": 48
+    },
+    {
+      "epoch": 0.15321477428180574,
+      "grad_norm": 1.635464072227478,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.5069,
+      "step": 49
+    },
+    {
+      "epoch": 0.15634160641000586,
+      "grad_norm": 2.803654432296753,
+      "learning_rate": 1e-05,
+      "loss": 2.9058,
+      "step": 50
+    },
+    {
+      "epoch": 0.15634160641000586,
+      "eval_loss": 2.43630313873291,
+      "eval_runtime": 1.9888,
+      "eval_samples_per_second": 25.14,
+      "eval_steps_per_second": 6.536,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null