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:f1c3bcb1afeee992104efc1f5046affde3fe86206016edabae5fdc48307b9481
+oid sha256:2992f1198b57545f3d96de735609dd8febdd24dc9c397424e9f357d4e303c4f2
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e5f2a774ba791da53c63d8fc0c7f17be8a0f351d602f7e75afb8ad60b0ac289
+oid sha256:b1d3bb119f4569152ce19be824d5fa4aa2c7499a033d0c7ff04097112c541e50
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:713a6cf4b6272f7621b298dabbc4473664bed2b520eb1a74901203d0af6ce719
+oid sha256:b5a11ddaf1fbf0a747cc7e8cbbfb3e4ff6476a7a9dd4f5b1562050488b575c1d
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d60e7b2c17b75edabe20816637bac7e0180942bea9fc1110d74706eb159692b3
+oid sha256:109d8ade748aaebb3c94e67d44363423d1c9adcaa4bd38ff06f09409c9e94f9f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16ef2c1dbee0f22ed696e31686752912c0486dec59583dc1b140dacc76dc2ed5
+oid sha256:26a8d5d3bc572a7b9ab824233d9163e8ce95957e2ec33c7db07d16bf20b1ad1d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be2a447a8965cd87b70d2f79358637a12e371dee73c5e1ad492ee47f6d1cb2de
+oid sha256:82b42616826e7c99e74818a240204380aa6cf354cb1a94651411d89032ce7c4c
 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": 0.002253216225653887,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.04589261128958238,
+  "best_metric": 0.0012522473698481917,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.09178522257916476,
   "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": 83.455,
       "eval_steps_per_second": 10.438,
       "step": 25
+    },
+    {
+      "epoch": 0.04772831574116567,
+      "grad_norm": 0.054946526885032654,
+      "learning_rate": 5e-05,
+      "loss": 0.0035,
+      "step": 26
+    },
+    {
+      "epoch": 0.04956402019274897,
+      "grad_norm": 0.049321189522743225,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0019,
+      "step": 27
+    },
+    {
+      "epoch": 0.05139972464433226,
+      "grad_norm": 0.04542066156864166,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.002,
+      "step": 28
+    },
+    {
+      "epoch": 0.05323542909591556,
+      "grad_norm": 0.09802614152431488,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0021,
+      "step": 29
+    },
+    {
+      "epoch": 0.05507113354749885,
+      "grad_norm": 0.061021555215120316,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0039,
+      "step": 30
+    },
+    {
+      "epoch": 0.056906837999082145,
+      "grad_norm": 0.03209061920642853,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0015,
+      "step": 31
+    },
+    {
+      "epoch": 0.058742542450665444,
+      "grad_norm": 0.03987056016921997,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0019,
+      "step": 32
+    },
+    {
+      "epoch": 0.060578246902248736,
+      "grad_norm": 0.014652871526777744,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0009,
+      "step": 33
+    },
+    {
+      "epoch": 0.062413951353832035,
+      "grad_norm": 0.03821863979101181,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0016,
+      "step": 34
+    },
+    {
+      "epoch": 0.06424965580541533,
+      "grad_norm": 0.03729190304875374,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0019,
+      "step": 35
+    },
+    {
+      "epoch": 0.06608536025699863,
+      "grad_norm": 0.029762962833046913,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.001,
+      "step": 36
+    },
+    {
+      "epoch": 0.06792106470858192,
+      "grad_norm": 0.01879103109240532,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0009,
+      "step": 37
+    },
+    {
+      "epoch": 0.06975676916016521,
+      "grad_norm": 0.0443434864282608,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0026,
+      "step": 38
+    },
+    {
+      "epoch": 0.0715924736117485,
+      "grad_norm": 0.07768885791301727,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0028,
+      "step": 39
+    },
+    {
+      "epoch": 0.07342817806333181,
+      "grad_norm": 0.03938576206564903,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0016,
+      "step": 40
+    },
+    {
+      "epoch": 0.0752638825149151,
+      "grad_norm": 0.03616311401128769,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0009,
+      "step": 41
+    },
+    {
+      "epoch": 0.07709958696649839,
+      "grad_norm": 0.01792808808386326,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0009,
+      "step": 42
+    },
+    {
+      "epoch": 0.07893529141808169,
+      "grad_norm": 0.0829036682844162,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0011,
+      "step": 43
+    },
+    {
+      "epoch": 0.08077099586966498,
+      "grad_norm": 0.03096242994070053,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0035,
+      "step": 44
+    },
+    {
+      "epoch": 0.08260670032124828,
+      "grad_norm": 0.05540601536631584,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0009,
+      "step": 45
+    },
+    {
+      "epoch": 0.08444240477283158,
+      "grad_norm": 0.021263469010591507,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0007,
+      "step": 46
+    },
+    {
+      "epoch": 0.08627810922441487,
+      "grad_norm": 0.05774582549929619,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0023,
+      "step": 47
+    },
+    {
+      "epoch": 0.08811381367599816,
+      "grad_norm": 0.03489619493484497,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0011,
+      "step": 48
+    },
+    {
+      "epoch": 0.08994951812758147,
+      "grad_norm": 0.017400847747921944,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0012,
+      "step": 49
+    },
+    {
+      "epoch": 0.09178522257916476,
+      "grad_norm": 0.07380491495132446,
+      "learning_rate": 0.0,
+      "loss": 0.0036,
+      "step": 50
+    },
+    {
+      "epoch": 0.09178522257916476,
+      "eval_loss": 0.0012522473698481917,
+      "eval_runtime": 41.0872,
+      "eval_samples_per_second": 89.322,
+      "eval_steps_per_second": 11.171,
+      "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": 5.300992813406618e+16,
+  "total_flos": 1.0598674582837658e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null