Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36d6f8e5b4c39aa35d3b715a69674b1cdca1655a1bd94eb02bcf297e9d652439
+oid sha256:6d5d266261c239f147c53d3d84b1b8ec88b587f92ac07d1bc6562f167567aeb8
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90c666913bae3c7291a4e7ff7741c225015d9de391d3301a1a127afc1e1ff92c
+oid sha256:334ee4b3c2255f422d1678b50ee86e6254e63ee7e01f829fe4d66880b68a351b
 size 180543866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f0af18924c3692370a232230ead190287435aa13ac5dd76ddc187ab90f74736
+oid sha256:a02569f3d7715204d360a61b69b98fdd383d4ba70c4b321404564bddc49914ba
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5ff0112122cc0613c5e05e16eb87755d607e327ad987a990cfa8b12aabe1f78
+oid sha256:b5718cdb2c393941c9b030f268fb5ff15c6b7eb890bcd7b868af95733724a772
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f47d92f36bfb25b18a28f502c440e6be71989b6dab7afa0c9f2981125ee4529d
+oid sha256:4c8ccbd5fa16cdabe69ebb4a73669eb82b03d95427eb88cf8ac7a6a5a7f6a1db
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:795c1562ae03dc6811efd623a701de2602863a39afb056b707a9f46b9779c769
+oid sha256:a87e53dba192e19e010fbdaf8dc8a83628dd187918b65ec11aaf4384fac5dbea
 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": 0.4012819528579712,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.08131734092295181,
+  "best_metric": 0.36945176124572754,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.16263468184590363,
   "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": 52.165,
       "eval_steps_per_second": 13.563,
       "step": 25
+    },
+    {
+      "epoch": 0.08457003455986989,
+      "grad_norm": 1.9013361930847168,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.3487,
+      "step": 26
+    },
+    {
+      "epoch": 0.08782272819678796,
+      "grad_norm": 1.1355395317077637,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.3625,
+      "step": 27
+    },
+    {
+      "epoch": 0.09107542183370604,
+      "grad_norm": 1.7093337774276733,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.3684,
+      "step": 28
+    },
+    {
+      "epoch": 0.09432811547062411,
+      "grad_norm": 2.666853427886963,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.4088,
+      "step": 29
+    },
+    {
+      "epoch": 0.09758080910754219,
+      "grad_norm": 3.9227817058563232,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.3787,
+      "step": 30
+    },
+    {
+      "epoch": 0.10083350274446026,
+      "grad_norm": 2.1414694786071777,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.3545,
+      "step": 31
+    },
+    {
+      "epoch": 0.10408619638137832,
+      "grad_norm": 2.217756986618042,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.3893,
+      "step": 32
+    },
+    {
+      "epoch": 0.1073388900182964,
+      "grad_norm": 1.2464871406555176,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.3589,
+      "step": 33
+    },
+    {
+      "epoch": 0.11059158365521447,
+      "grad_norm": 2.3798458576202393,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.3977,
+      "step": 34
+    },
+    {
+      "epoch": 0.11384427729213255,
+      "grad_norm": 0.625939667224884,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.3654,
+      "step": 35
+    },
+    {
+      "epoch": 0.11709697092905062,
+      "grad_norm": 1.7202353477478027,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.3876,
+      "step": 36
+    },
+    {
+      "epoch": 0.1203496645659687,
+      "grad_norm": 3.1904664039611816,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.3818,
+      "step": 37
+    },
+    {
+      "epoch": 0.12360235820288677,
+      "grad_norm": 2.18723201751709,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.4145,
+      "step": 38
+    },
+    {
+      "epoch": 0.12685505183980483,
+      "grad_norm": 5.541439533233643,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.4644,
+      "step": 39
+    },
+    {
+      "epoch": 0.1301077454767229,
+      "grad_norm": 5.606419563293457,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.4775,
+      "step": 40
+    },
+    {
+      "epoch": 0.13336043911364098,
+      "grad_norm": 3.325843095779419,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.4146,
+      "step": 41
+    },
+    {
+      "epoch": 0.13661313275055906,
+      "grad_norm": 2.5272328853607178,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.3798,
+      "step": 42
+    },
+    {
+      "epoch": 0.13986582638747713,
+      "grad_norm": 0.6817333102226257,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.3452,
+      "step": 43
+    },
+    {
+      "epoch": 0.1431185200243952,
+      "grad_norm": 0.49600663781166077,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.3539,
+      "step": 44
+    },
+    {
+      "epoch": 0.14637121366131328,
+      "grad_norm": 1.7873883247375488,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.3806,
+      "step": 45
+    },
+    {
+      "epoch": 0.14962390729823136,
+      "grad_norm": 2.138842821121216,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.3836,
+      "step": 46
+    },
+    {
+      "epoch": 0.15287660093514943,
+      "grad_norm": 1.6219154596328735,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.3823,
+      "step": 47
+    },
+    {
+      "epoch": 0.1561292945720675,
+      "grad_norm": 2.0069103240966797,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.3583,
+      "step": 48
+    },
+    {
+      "epoch": 0.15938198820898555,
+      "grad_norm": 3.421016216278076,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.4189,
+      "step": 49
+    },
+    {
+      "epoch": 0.16263468184590363,
+      "grad_norm": 2.984545946121216,
+      "learning_rate": 1e-05,
+      "loss": 0.4189,
+      "step": 50
+    },
+    {
+      "epoch": 0.16263468184590363,
+      "eval_loss": 0.36945176124572754,
+      "eval_runtime": 0.9603,
+      "eval_samples_per_second": 52.065,
+      "eval_steps_per_second": 13.537,
+      "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": 3.91521434075136e+16,
+  "total_flos": 7.83042868150272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null