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:d212743c0c6b98949d9bc4174906090ba6b88f460674cc966a7097e08820571b
+oid sha256:e040cd2ca8aebfa94911beb06e74cf553b6be80700bd0c20a446cefcb86e601f
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:752e39749dbd081f613e7dad5892fb881fb07c31aced028a6c68cac682c54fc4
+oid sha256:6affba065e17843d6095678549fefbf3a2885f74cba96c6507a1de06202e7af2
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:245fae4b7f658c63282c8ae397ee23ff3bf25154def8c0d530781a60a0220918
+oid sha256:5682926293910259edfad0b00d8b1f02dc8ca3a174609117d1f3a3c960fce2cf
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d16230bb592b24ff21f790ec1646926276cc457d7b326e8494afdaadbc48f51c
+oid sha256:8b404979d7c1f26c77f57bf97514d6bba03c80c977b7d0fbb195c18f9bb0436a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00ab4e3619dc4c03eff46ee14e28f131ba18595404bd9f41560dd0867f575529
+oid sha256:22d7e3d1f5ca36d2e3541c2b0ed184827782955b2ca0df44bd30d4c2b7fd994d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68f417716e8b4f6814c064ce3af6f5c4666de0aea75ed3481bac6205b829cbd0
+oid sha256:8530b0d42776972af49a28fb2a122325971025d6a7c47d6e2ae81874b1ac457d
 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": 1.797715187072754,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.032030749519538756,
+  "best_metric": 1.7794197797775269,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06406149903907751,
   "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": 88.5,
       "eval_steps_per_second": 11.075,
       "step": 25
+    },
+    {
+      "epoch": 0.033311979500320305,
+      "grad_norm": 0.42451655864715576,
+      "learning_rate": 5e-05,
+      "loss": 1.7534,
+      "step": 26
+    },
+    {
+      "epoch": 0.03459320948110186,
+      "grad_norm": 0.4029790759086609,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.6702,
+      "step": 27
+    },
+    {
+      "epoch": 0.03587443946188341,
+      "grad_norm": 0.4106031656265259,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.7286,
+      "step": 28
+    },
+    {
+      "epoch": 0.037155669442664956,
+      "grad_norm": 0.40695980191230774,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.7776,
+      "step": 29
+    },
+    {
+      "epoch": 0.03843689942344651,
+      "grad_norm": 0.41555243730545044,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.8432,
+      "step": 30
+    },
+    {
+      "epoch": 0.03971812940422806,
+      "grad_norm": 0.4222233295440674,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.7395,
+      "step": 31
+    },
+    {
+      "epoch": 0.04099935938500961,
+      "grad_norm": 0.4671240448951721,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.7829,
+      "step": 32
+    },
+    {
+      "epoch": 0.04228058936579116,
+      "grad_norm": 0.40571528673171997,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.8406,
+      "step": 33
+    },
+    {
+      "epoch": 0.04356181934657271,
+      "grad_norm": 0.4159633219242096,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.84,
+      "step": 34
+    },
+    {
+      "epoch": 0.04484304932735426,
+      "grad_norm": 0.4444989562034607,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.7806,
+      "step": 35
+    },
+    {
+      "epoch": 0.04612427930813581,
+      "grad_norm": 0.44324401021003723,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.8427,
+      "step": 36
+    },
+    {
+      "epoch": 0.04740550928891736,
+      "grad_norm": 0.5288540720939636,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.8759,
+      "step": 37
+    },
+    {
+      "epoch": 0.04868673926969891,
+      "grad_norm": 0.4690561294555664,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.7791,
+      "step": 38
+    },
+    {
+      "epoch": 0.049967969250480464,
+      "grad_norm": 0.41271162033081055,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.6678,
+      "step": 39
+    },
+    {
+      "epoch": 0.05124919923126201,
+      "grad_norm": 0.398227721452713,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.7866,
+      "step": 40
+    },
+    {
+      "epoch": 0.05253042921204356,
+      "grad_norm": 0.4064875841140747,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.8097,
+      "step": 41
+    },
+    {
+      "epoch": 0.053811659192825115,
+      "grad_norm": 0.3928537368774414,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.6876,
+      "step": 42
+    },
+    {
+      "epoch": 0.05509288917360666,
+      "grad_norm": 0.3979778289794922,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.8318,
+      "step": 43
+    },
+    {
+      "epoch": 0.05637411915438821,
+      "grad_norm": 0.38359037041664124,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.8171,
+      "step": 44
+    },
+    {
+      "epoch": 0.057655349135169766,
+      "grad_norm": 0.40605178475379944,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.829,
+      "step": 45
+    },
+    {
+      "epoch": 0.058936579115951314,
+      "grad_norm": 0.3973970413208008,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.8294,
+      "step": 46
+    },
+    {
+      "epoch": 0.06021780909673286,
+      "grad_norm": 0.4090547263622284,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.8194,
+      "step": 47
+    },
+    {
+      "epoch": 0.06149903907751442,
+      "grad_norm": 0.41120144724845886,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.7599,
+      "step": 48
+    },
+    {
+      "epoch": 0.06278026905829596,
+      "grad_norm": 0.46502575278282166,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.7705,
+      "step": 49
+    },
+    {
+      "epoch": 0.06406149903907751,
+      "grad_norm": 0.6171591281890869,
+      "learning_rate": 0.0,
+      "loss": 1.807,
+      "step": 50
+    },
+    {
+      "epoch": 0.06406149903907751,
+      "eval_loss": 1.7794197797775269,
+      "eval_runtime": 59.439,
+      "eval_samples_per_second": 88.46,
+      "eval_steps_per_second": 11.07,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null