Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ee077d36bf938ac065ae3e22e3966eec98616fc5d83cc2b64ed8b9caf7c11d9
+oid sha256:45b0cf1c54bab93294983e046f5eba2ea3f4cf6e74466fa2ef83b6ac77bf604e
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57b5954d942d7d730ba66fe0ce50078d625529ba359a796bb8a5d1dc575bbcf8
+oid sha256:63dfec217d03a0a3fde0f8ed2148029ba5da56a73d1232ccb107f9cb25dfef10
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35c6f312ac69f384ea4874eb0a5c4c91843aec32e937dd5c88d95e88d728da80
+oid sha256:1782043dd432c3e5949b16ffba08fd943db5118a3ecf077679af4a604242e469
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73f8d00ca2d13dce36c106a400f230b4acc8987435a04336a020333773bdf196
+oid sha256:42ee3960f5ef11d98f706f693873118122861abf3288d50c2c87e3558117a6da
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:934cfc81fad8df2c509f632f35514b3849bcb8ed44cf8724cd30de72a7f304d6
+oid sha256:580d0ebbf03d8b3d8b79301fb4d1ca3ea03f83f5d19721893f9c1a093c4d5df5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d9fb61345796b8625184fdaaa7f35a47a1c2406c127136d62947ab2234bee01
+oid sha256:a0605049c99910af9850dc577ef6c085ad309260e980d16c9453ccffa6b69fbc
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 4.299006938934326,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.03374957813027337,
+  "best_metric": 3.9180445671081543,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06749915626054674,
   "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": 13.513,
       "eval_steps_per_second": 1.69,
       "step": 25
+    },
+    {
+      "epoch": 0.03509956125548431,
+      "grad_norm": 8.628137588500977,
+      "learning_rate": 5e-05,
+      "loss": 3.2233,
+      "step": 26
+    },
+    {
+      "epoch": 0.03644954438069524,
+      "grad_norm": 10.846193313598633,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 3.8442,
+      "step": 27
+    },
+    {
+      "epoch": 0.03779952750590618,
+      "grad_norm": 8.67941951751709,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 3.9179,
+      "step": 28
+    },
+    {
+      "epoch": 0.03914951063111711,
+      "grad_norm": 7.8950676918029785,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 3.7976,
+      "step": 29
+    },
+    {
+      "epoch": 0.040499493756328046,
+      "grad_norm": 6.960816860198975,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 3.9247,
+      "step": 30
+    },
+    {
+      "epoch": 0.041849476881538984,
+      "grad_norm": 5.280318737030029,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 4.0847,
+      "step": 31
+    },
+    {
+      "epoch": 0.043199460006749915,
+      "grad_norm": 5.189662933349609,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 4.0055,
+      "step": 32
+    },
+    {
+      "epoch": 0.04454944313196085,
+      "grad_norm": 8.99771785736084,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 4.3989,
+      "step": 33
+    },
+    {
+      "epoch": 0.045899426257171784,
+      "grad_norm": 7.683967113494873,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 4.4733,
+      "step": 34
+    },
+    {
+      "epoch": 0.04724940938238272,
+      "grad_norm": 7.3979105949401855,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 4.586,
+      "step": 35
+    },
+    {
+      "epoch": 0.04859939250759365,
+      "grad_norm": 11.688506126403809,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 4.817,
+      "step": 36
+    },
+    {
+      "epoch": 0.04994937563280459,
+      "grad_norm": 11.070033073425293,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 4.984,
+      "step": 37
+    },
+    {
+      "epoch": 0.05129935875801552,
+      "grad_norm": 4.192941188812256,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.1219,
+      "step": 38
+    },
+    {
+      "epoch": 0.05264934188322646,
+      "grad_norm": 5.510909080505371,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 3.3148,
+      "step": 39
+    },
+    {
+      "epoch": 0.0539993250084374,
+      "grad_norm": 5.6417131423950195,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 3.3338,
+      "step": 40
+    },
+    {
+      "epoch": 0.05534930813364833,
+      "grad_norm": 5.337092399597168,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 3.639,
+      "step": 41
+    },
+    {
+      "epoch": 0.056699291258859266,
+      "grad_norm": 4.77625036239624,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 3.5133,
+      "step": 42
+    },
+    {
+      "epoch": 0.0580492743840702,
+      "grad_norm": 4.821012496948242,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 3.9282,
+      "step": 43
+    },
+    {
+      "epoch": 0.059399257509281135,
+      "grad_norm": 4.676504135131836,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.9006,
+      "step": 44
+    },
+    {
+      "epoch": 0.060749240634492066,
+      "grad_norm": 4.670116901397705,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 3.9759,
+      "step": 45
+    },
+    {
+      "epoch": 0.062099223759703004,
+      "grad_norm": 5.629438400268555,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 4.2648,
+      "step": 46
+    },
+    {
+      "epoch": 0.06344920688491394,
+      "grad_norm": 5.580984592437744,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 4.3399,
+      "step": 47
+    },
+    {
+      "epoch": 0.06479919001012488,
+      "grad_norm": 5.877447605133057,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 4.4184,
+      "step": 48
+    },
+    {
+      "epoch": 0.0661491731353358,
+      "grad_norm": 8.028692245483398,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 4.8048,
+      "step": 49
+    },
+    {
+      "epoch": 0.06749915626054674,
+      "grad_norm": 8.630199432373047,
+      "learning_rate": 0.0,
+      "loss": 4.78,
+      "step": 50
+    },
+    {
+      "epoch": 0.06749915626054674,
+      "eval_loss": 3.9180445671081543,
+      "eval_runtime": 369.3832,
+      "eval_samples_per_second": 13.509,
+      "eval_steps_per_second": 1.689,
+      "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": 3.087239672233984e+17,
+  "total_flos": 6.174479344467968e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null