Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ed22eb2d7e6f9c29532663c45bb16ae807469731d016648fd63306a60eed35e
+oid sha256:c2cf0d4c211e53b221e19f5989209598444dd023de41c90b9fe88cf294bcb95b
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b39ebf434623be471765a3dc9b4ea7d53d4413e87eb439cc58bf7694ba52c58
+oid sha256:247bf23715b6180ee52405985ed7042a28d5e5373830490f8139d4fe6c702a6b
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3d78a35e42b9efcfe34b4967c7f0f8d66fb938a5136c6189e78f26d89484a14
+oid sha256:adcdfee27c75495036d6829c6db3c43e011b6d1380b2b41e7eb84cad758bb40a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a398c509feb813baa97b10d1eedbe0b29922ebcdb6ca795b424a3ad2fd4fd0f0
+oid sha256:57d480f79ec421b7e0a9e4d21edd0c2c54631fa353ecf03cff77cfd37488fbf8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e75324fe76ed92099f7d03ddcf988c75e340f2bb6df76aaf6e2a63b88447609
+oid sha256:b522dc2bcdfce09ace0a2922fe68f677c422b00f4dbcf7a723a60e9b598bab5a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b44a7bf89921658387e8b066b317c1d70bd89d57fea882ec6829807a2397ff75
+oid sha256:ddbab581915d89fbc6c89621935cd4473bf7975c58ad51900b9233a91f9da4b8
 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": 4.303714752197266,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.30627871362940273,
+  "best_metric": 4.124782085418701,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6125574272588055,
   "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": 14.307,
       "eval_steps_per_second": 3.72,
       "step": 25
+    },
+    {
+      "epoch": 0.31852986217457885,
+      "grad_norm": 7.1779561042785645,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 3.17,
+      "step": 26
+    },
+    {
+      "epoch": 0.33078101071975496,
+      "grad_norm": 3.5469911098480225,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 3.5137,
+      "step": 27
+    },
+    {
+      "epoch": 0.3430321592649311,
+      "grad_norm": 2.8225502967834473,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 3.2536,
+      "step": 28
+    },
+    {
+      "epoch": 0.3552833078101072,
+      "grad_norm": 3.2358927726745605,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 3.4745,
+      "step": 29
+    },
+    {
+      "epoch": 0.3675344563552833,
+      "grad_norm": 4.149901390075684,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.6246,
+      "step": 30
+    },
+    {
+      "epoch": 0.37978560490045943,
+      "grad_norm": 3.0618069171905518,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 3.6646,
+      "step": 31
+    },
+    {
+      "epoch": 0.39203675344563554,
+      "grad_norm": 4.720259189605713,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 3.8053,
+      "step": 32
+    },
+    {
+      "epoch": 0.40428790199081166,
+      "grad_norm": 2.7804815769195557,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 3.3949,
+      "step": 33
+    },
+    {
+      "epoch": 0.4165390505359878,
+      "grad_norm": 3.4043445587158203,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 3.8051,
+      "step": 34
+    },
+    {
+      "epoch": 0.42879019908116384,
+      "grad_norm": 3.489053964614868,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 3.7363,
+      "step": 35
+    },
+    {
+      "epoch": 0.44104134762633995,
+      "grad_norm": 3.47819185256958,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 3.6668,
+      "step": 36
+    },
+    {
+      "epoch": 0.45329249617151607,
+      "grad_norm": 3.2192630767822266,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 4.1236,
+      "step": 37
+    },
+    {
+      "epoch": 0.4655436447166922,
+      "grad_norm": 3.5141780376434326,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 3.3018,
+      "step": 38
+    },
+    {
+      "epoch": 0.4777947932618683,
+      "grad_norm": 3.293383836746216,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 3.3655,
+      "step": 39
+    },
+    {
+      "epoch": 0.4900459418070444,
+      "grad_norm": 3.6325714588165283,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 3.5624,
+      "step": 40
+    },
+    {
+      "epoch": 0.5022970903522205,
+      "grad_norm": 3.457775354385376,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 3.7964,
+      "step": 41
+    },
+    {
+      "epoch": 0.5145482388973966,
+      "grad_norm": 2.97334623336792,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 3.7029,
+      "step": 42
+    },
+    {
+      "epoch": 0.5267993874425727,
+      "grad_norm": 3.7691123485565186,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 3.9081,
+      "step": 43
+    },
+    {
+      "epoch": 0.5390505359877489,
+      "grad_norm": 3.316641092300415,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 4.0407,
+      "step": 44
+    },
+    {
+      "epoch": 0.5513016845329249,
+      "grad_norm": 3.486757755279541,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 3.9519,
+      "step": 45
+    },
+    {
+      "epoch": 0.5635528330781011,
+      "grad_norm": 3.3748724460601807,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 3.8977,
+      "step": 46
+    },
+    {
+      "epoch": 0.5758039816232772,
+      "grad_norm": 3.2216415405273438,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 4.1025,
+      "step": 47
+    },
+    {
+      "epoch": 0.5880551301684533,
+      "grad_norm": 4.37778902053833,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 3.7138,
+      "step": 48
+    },
+    {
+      "epoch": 0.6003062787136294,
+      "grad_norm": 4.192712306976318,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 4.0474,
+      "step": 49
+    },
+    {
+      "epoch": 0.6125574272588055,
+      "grad_norm": 4.064006805419922,
+      "learning_rate": 1e-05,
+      "loss": 4.2144,
+      "step": 50
+    },
+    {
+      "epoch": 0.6125574272588055,
+      "eval_loss": 4.124782085418701,
+      "eval_runtime": 3.5052,
+      "eval_samples_per_second": 14.265,
+      "eval_steps_per_second": 3.709,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null