Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3256b676fb0101f7be6fc52b082f2b744ac32c792b4975c4c8306b8db207db01
+oid sha256:66a95781b7e9f2379c09560b65861531e2b13b33351fa8f6f0be9686121351ed
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:755da9cd6697f00cfc4ed0cc3bd17aa6a3ffbc9e34eb278466289e4e4200141f
+oid sha256:67371dcbb4bbd3029270a713bdeb39582a8c3f4f2b7c3ba162d8cf69d172c737
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3f1f330b91a01ecca13dc7b80d4a5f72f11e1d682488ffe337e5593f38ced84
+oid sha256:0f103fec545ad6a028c887b64ae9843d495660089339c8517c55965dfce7aba2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93bbd3544d95a84a70334ebc6b1e0ad6b8f967ee270228c95e9a3668308dcc4e
+oid sha256:db9aaf4561d7786580e6d8a4ad4209cf93a3efa8aae9a9ecfa7deb0512b286f4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:775d6556671c37881928625ebed6a59acf3d4abf72ae8202047a303e132ab0cf
+oid sha256:f6359b7e3112d7ecdfe9dd8199bae5cb12c86d5a16a81caceb9da261025d606a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:445e9de3e469ea3be8400bad746515b4d13a37504696cea53941512b97a65123
+oid sha256:dbc22d26c1c23724e49c2f8fe31ecfca3afda963b0fc16b767b7c85dc52ad02e
 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": 5.417140483856201,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.1225626740947074,
+  "best_metric": 4.716582775115967,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.245125348189415,
   "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": 27.245,
       "eval_steps_per_second": 7.084,
       "step": 25
+    },
+    {
+      "epoch": 1.1671309192200556,
+      "grad_norm": 2.453505516052246,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 5.583,
+      "step": 26
+    },
+    {
+      "epoch": 1.2116991643454038,
+      "grad_norm": 2.5713016986846924,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 5.6186,
+      "step": 27
+    },
+    {
+      "epoch": 1.2562674094707522,
+      "grad_norm": 1.9322009086608887,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 3.9696,
+      "step": 28
+    },
+    {
+      "epoch": 1.3008356545961002,
+      "grad_norm": 2.791020631790161,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 4.4587,
+      "step": 29
+    },
+    {
+      "epoch": 1.3454038997214486,
+      "grad_norm": 2.149622917175293,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 4.8004,
+      "step": 30
+    },
+    {
+      "epoch": 1.3899721448467965,
+      "grad_norm": 2.2228457927703857,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 5.1657,
+      "step": 31
+    },
+    {
+      "epoch": 1.434540389972145,
+      "grad_norm": 2.323864221572876,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 5.0189,
+      "step": 32
+    },
+    {
+      "epoch": 1.479108635097493,
+      "grad_norm": 2.922153949737549,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 5.52,
+      "step": 33
+    },
+    {
+      "epoch": 1.5236768802228413,
+      "grad_norm": 2.770920515060425,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 4.2389,
+      "step": 34
+    },
+    {
+      "epoch": 1.5682451253481893,
+      "grad_norm": 2.918221950531006,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 4.0683,
+      "step": 35
+    },
+    {
+      "epoch": 1.6128133704735377,
+      "grad_norm": 2.5188300609588623,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 5.1571,
+      "step": 36
+    },
+    {
+      "epoch": 1.6573816155988856,
+      "grad_norm": 2.6808626651763916,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 5.0721,
+      "step": 37
+    },
+    {
+      "epoch": 1.701949860724234,
+      "grad_norm": 1.907468318939209,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 5.1194,
+      "step": 38
+    },
+    {
+      "epoch": 1.7465181058495822,
+      "grad_norm": 1.6851441860198975,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 3.4621,
+      "step": 39
+    },
+    {
+      "epoch": 1.7910863509749304,
+      "grad_norm": 2.436414957046509,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 4.29,
+      "step": 40
+    },
+    {
+      "epoch": 1.8356545961002786,
+      "grad_norm": 1.9236414432525635,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 4.988,
+      "step": 41
+    },
+    {
+      "epoch": 1.8802228412256268,
+      "grad_norm": 1.9346405267715454,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 4.5542,
+      "step": 42
+    },
+    {
+      "epoch": 1.924791086350975,
+      "grad_norm": 2.173877000808716,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 4.9275,
+      "step": 43
+    },
+    {
+      "epoch": 1.9693593314763231,
+      "grad_norm": 3.563979148864746,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 5.8462,
+      "step": 44
+    },
+    {
+      "epoch": 2.022284122562674,
+      "grad_norm": 3.204674005508423,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 7.8565,
+      "step": 45
+    },
+    {
+      "epoch": 2.066852367688022,
+      "grad_norm": 1.8876923322677612,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 3.5769,
+      "step": 46
+    },
+    {
+      "epoch": 2.1114206128133706,
+      "grad_norm": 1.8125336170196533,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 4.7022,
+      "step": 47
+    },
+    {
+      "epoch": 2.1559888579387185,
+      "grad_norm": 1.8523550033569336,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 4.4587,
+      "step": 48
+    },
+    {
+      "epoch": 2.200557103064067,
+      "grad_norm": 2.4004316329956055,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 4.7921,
+      "step": 49
+    },
+    {
+      "epoch": 2.245125348189415,
+      "grad_norm": 1.909448504447937,
+      "learning_rate": 1e-05,
+      "loss": 2.6394,
+      "step": 50
+    },
+    {
+      "epoch": 2.245125348189415,
+      "eval_loss": 4.716582775115967,
+      "eval_runtime": 1.8513,
+      "eval_samples_per_second": 27.009,
+      "eval_steps_per_second": 7.022,
+      "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": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null