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:a92672439c1876c0fcda6282df8e5e949e37f27e968f1758c9dfe5e9d7fae30d
+oid sha256:042026c57c119adb2abf5e22719264e5f409c9727074e599b9545d9d6d768325
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07c8dc6b3c52ba757f2a249b44cd3b9710384f13240d671709008775f34c191d
+oid sha256:57d822b67a5b3619e720c5454f7534170bcb052716ff63acded16ae450c7542b
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4804cf6371185859667fb5b0fa4d43a9812a9bd3ab8b634638133d18aa929836
+oid sha256:dc29e05449f31d2e94394fe59c01418c1e6241105ae91a574118848146584415
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3671b4d31690114bcb2d3d21e46ebb94897ddd1b52e483e18e8d3e5027e39585
+oid sha256:0b697b807dd856c5585e6f159ccc2fe3304e089d2f6a459585cd4bb7d8fc8c45
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2a509c06aa9aa8994390b832621ef1df7afbbe1ea85af2cb9d738b26a4ac119
+oid sha256:37348e8f1362242ee92b948ae1f313a93d616b75b1564899f7d36babda63ac7a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b3def97aa272b8007a3a152648b9f21f696b29a91fabb8b7041dec4a935a84d
+oid sha256:90956b7fee71f0ca23ef07e1ec38592ba5c343271f722210bb44be50c5179e66
 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": 2.6764278411865234,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.7714561234329798,
+  "best_metric": 2.542440414428711,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.5429122468659595,
   "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": 49.072,
       "eval_steps_per_second": 12.759,
       "step": 25
+    },
+    {
+      "epoch": 0.8023143683702989,
+      "grad_norm": 0.6719350814819336,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.6062,
+      "step": 26
+    },
+    {
+      "epoch": 0.8331726133076182,
+      "grad_norm": 0.7067621946334839,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.6239,
+      "step": 27
+    },
+    {
+      "epoch": 0.8640308582449373,
+      "grad_norm": 0.7096052765846252,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.6449,
+      "step": 28
+    },
+    {
+      "epoch": 0.8948891031822566,
+      "grad_norm": 0.9343886971473694,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.7355,
+      "step": 29
+    },
+    {
+      "epoch": 0.9257473481195757,
+      "grad_norm": 0.8786309957504272,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.7085,
+      "step": 30
+    },
+    {
+      "epoch": 0.9566055930568949,
+      "grad_norm": 1.608211636543274,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.8077,
+      "step": 31
+    },
+    {
+      "epoch": 0.9874638379942141,
+      "grad_norm": 3.240671157836914,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 3.0358,
+      "step": 32
+    },
+    {
+      "epoch": 1.0183220829315334,
+      "grad_norm": 0.9655975103378296,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 4.2671,
+      "step": 33
+    },
+    {
+      "epoch": 1.0491803278688525,
+      "grad_norm": 0.45573168992996216,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.4911,
+      "step": 34
+    },
+    {
+      "epoch": 1.0800385728061717,
+      "grad_norm": 0.6124336123466492,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.5842,
+      "step": 35
+    },
+    {
+      "epoch": 1.1108968177434908,
+      "grad_norm": 0.7188212275505066,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.6513,
+      "step": 36
+    },
+    {
+      "epoch": 1.14175506268081,
+      "grad_norm": 0.6598315238952637,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 2.5331,
+      "step": 37
+    },
+    {
+      "epoch": 1.1726133076181293,
+      "grad_norm": 0.8761363625526428,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.683,
+      "step": 38
+    },
+    {
+      "epoch": 1.2034715525554485,
+      "grad_norm": 1.1395080089569092,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.8706,
+      "step": 39
+    },
+    {
+      "epoch": 1.2343297974927676,
+      "grad_norm": 2.4882192611694336,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.8492,
+      "step": 40
+    },
+    {
+      "epoch": 1.2651880424300868,
+      "grad_norm": 1.7844231128692627,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.3893,
+      "step": 41
+    },
+    {
+      "epoch": 1.296046287367406,
+      "grad_norm": 0.4351036250591278,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.4818,
+      "step": 42
+    },
+    {
+      "epoch": 1.326904532304725,
+      "grad_norm": 0.5659633874893188,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.5207,
+      "step": 43
+    },
+    {
+      "epoch": 1.3577627772420444,
+      "grad_norm": 0.6583766937255859,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.5642,
+      "step": 44
+    },
+    {
+      "epoch": 1.3886210221793636,
+      "grad_norm": 0.7262064218521118,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.5321,
+      "step": 45
+    },
+    {
+      "epoch": 1.4194792671166827,
+      "grad_norm": 0.8103611469268799,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.5716,
+      "step": 46
+    },
+    {
+      "epoch": 1.4503375120540019,
+      "grad_norm": 1.1891920566558838,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.8041,
+      "step": 47
+    },
+    {
+      "epoch": 1.4811957569913212,
+      "grad_norm": 2.4868645668029785,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.8477,
+      "step": 48
+    },
+    {
+      "epoch": 1.5120540019286404,
+      "grad_norm": 1.4715479612350464,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.3655,
+      "step": 49
+    },
+    {
+      "epoch": 1.5429122468659595,
+      "grad_norm": 0.4287128448486328,
+      "learning_rate": 1e-05,
+      "loss": 2.4207,
+      "step": 50
+    },
+    {
+      "epoch": 1.5429122468659595,
+      "eval_loss": 2.542440414428711,
+      "eval_runtime": 1.0194,
+      "eval_samples_per_second": 49.047,
+      "eval_steps_per_second": 12.752,
+      "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": 4.169686374888243e+16,
+  "total_flos": 8.34067497043886e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null