Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7baec5a4648a46982a46b51c52db99790328edbdc68884f337421de229b10332
+oid sha256:87925e29b036ef38ec4e5d908402af8d01da4ec252954e99de891201cbc82bec
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07c0ae3d3620a9425b4c1db25e26fed30ee75a59668bb9867ab6844e1e81243c
+oid sha256:e497043d073123b09d588e1f2cfb45e665b7a4c61dfd3e5386a4b5f71d4cb8a0
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdc5037155dff90f70f4947182f46934f7798e0cbe4ec9375d6a85ae50362527
+oid sha256:be6eadfa8f70380c1c8b94eb0135f51796dc6a7978f52044792844da362f5c5e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0f1478724a221dea59378c52b3411d39b6c6ed477887e6033cad783b6eb1d5f
+oid sha256:9bdd11cb1b2e3e6f92617a79d88567cd092f03186b61640bcdf3ac1be37aa193
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eba6687867de05bb0306dccdfbc5a5a60e007a2331095bdaa105bfd519bbe35f
+oid sha256:1e987ac867c6082951873e969d8fe5b4d9cb4fb037fafb6c80c682472abd9230
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90ea921e1d8524727e146f1aee2f9146030a41c568af6c47117a5111a46ed983
+oid sha256:1f61d92cd972c27c76295981a7a7c62aef935f239c07f184d50307b7a8871b29
 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": 10.349185943603516,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.22111663902708678,
+  "best_metric": 10.332913398742676,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.44223327805417356,
   "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": 511.674,
       "eval_steps_per_second": 133.035,
       "step": 25
+    },
+    {
+      "epoch": 0.22996130458817027,
+      "grad_norm": 0.36061304807662964,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.3556,
+      "step": 26
+    },
+    {
+      "epoch": 0.23880597014925373,
+      "grad_norm": 0.3968428373336792,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 10.3482,
+      "step": 27
+    },
+    {
+      "epoch": 0.2476506357103372,
+      "grad_norm": 0.494952529668808,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 10.3479,
+      "step": 28
+    },
+    {
+      "epoch": 0.2564953012714207,
+      "grad_norm": 0.44858163595199585,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 10.3406,
+      "step": 29
+    },
+    {
+      "epoch": 0.26533996683250416,
+      "grad_norm": 0.47938835620880127,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 10.3479,
+      "step": 30
+    },
+    {
+      "epoch": 0.2741846323935876,
+      "grad_norm": 0.47682392597198486,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 10.3402,
+      "step": 31
+    },
+    {
+      "epoch": 0.2830292979546711,
+      "grad_norm": 0.4649764895439148,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 10.3483,
+      "step": 32
+    },
+    {
+      "epoch": 0.29187396351575456,
+      "grad_norm": 0.5086086392402649,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 10.3499,
+      "step": 33
+    },
+    {
+      "epoch": 0.30071862907683805,
+      "grad_norm": 0.48151227831840515,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 10.3411,
+      "step": 34
+    },
+    {
+      "epoch": 0.3095632946379215,
+      "grad_norm": 0.45083463191986084,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 10.3495,
+      "step": 35
+    },
+    {
+      "epoch": 0.31840796019900497,
+      "grad_norm": 0.4745575785636902,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 10.3501,
+      "step": 36
+    },
+    {
+      "epoch": 0.32725262576008846,
+      "grad_norm": 0.4784848093986511,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 10.3442,
+      "step": 37
+    },
+    {
+      "epoch": 0.33609729132117194,
+      "grad_norm": 0.45313701033592224,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 10.3468,
+      "step": 38
+    },
+    {
+      "epoch": 0.3449419568822554,
+      "grad_norm": 0.5286972522735596,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 10.3411,
+      "step": 39
+    },
+    {
+      "epoch": 0.35378662244333886,
+      "grad_norm": 0.4753875732421875,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 10.342,
+      "step": 40
+    },
+    {
+      "epoch": 0.36263128800442235,
+      "grad_norm": 0.510720431804657,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 10.3428,
+      "step": 41
+    },
+    {
+      "epoch": 0.3714759535655058,
+      "grad_norm": 0.44279390573501587,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 10.3392,
+      "step": 42
+    },
+    {
+      "epoch": 0.38032061912658927,
+      "grad_norm": 0.5358765721321106,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 10.337,
+      "step": 43
+    },
+    {
+      "epoch": 0.38916528468767275,
+      "grad_norm": 0.48339778184890747,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 10.3464,
+      "step": 44
+    },
+    {
+      "epoch": 0.39800995024875624,
+      "grad_norm": 0.5888710618019104,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 10.3369,
+      "step": 45
+    },
+    {
+      "epoch": 0.40685461580983967,
+      "grad_norm": 0.5486493110656738,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 10.3352,
+      "step": 46
+    },
+    {
+      "epoch": 0.41569928137092316,
+      "grad_norm": 0.5062825083732605,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 10.3399,
+      "step": 47
+    },
+    {
+      "epoch": 0.42454394693200664,
+      "grad_norm": 0.4957694411277771,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 10.3394,
+      "step": 48
+    },
+    {
+      "epoch": 0.43338861249309013,
+      "grad_norm": 0.4638318419456482,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 10.3439,
+      "step": 49
+    },
+    {
+      "epoch": 0.44223327805417356,
+      "grad_norm": 0.5136078596115112,
+      "learning_rate": 1e-05,
+      "loss": 10.3451,
+      "step": 50
+    },
+    {
+      "epoch": 0.44223327805417356,
+      "eval_loss": 10.332913398742676,
+      "eval_runtime": 0.0906,
+      "eval_samples_per_second": 551.673,
+      "eval_steps_per_second": 143.435,
+      "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": 21384029798400.0,
+  "total_flos": 42768059596800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null