Training in progress, step 2134, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:784ba4d6b323f80b32bdeb7a699b9493ed33877eb1f5a4680739df590c874265
+oid sha256:a10f2f471ddb68aeb84eaedafdfdcf37d93db8b63aabad73c90654c0ff2b5c6c
 size 735217848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:463d10606216eaac5990abb66ecffc932b652d3d4835e35f52c38d3e543733ff
+oid sha256:786bac647cdfb3e95caf79a33fc77addeb1581415ccb52e3e6a59e8aa9baf708
 size 1470521978

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0886b5e6b4eb6c54d008834760837138a75d96ac8156628b1654cc847af0e990
+oid sha256:0e929bfb8d61dabc9ff9440d99be02b793be97dcf206c259cdc957e3702b21cb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd992b247e47b39b5cc00365846a4ed7e75fe3dd899b2263e283f44789d5c49b
+oid sha256:0470658ec86377919cf99d26abf4d40a040955151803301b44a6b653da17e99d
 size 1000

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9372071227741331,
+  "epoch": 1.0,
   "eval_steps": 100,
-  "global_step": 2000,
+  "global_step": 2134,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1727,6 +1727,113 @@
       "eval_spearman_manhattan": 0.8295593456330026,
       "eval_steps_per_second": 15.61,
       "step": 2000
+    },
+    {
+      "epoch": 0.9418931583880038,
+      "grad_norm": 1.1670805215835571,
+      "learning_rate": 4.411316776007498e-05,
+      "loss": 0.2544,
+      "step": 2010
+    },
+    {
+      "epoch": 0.9465791940018744,
+      "grad_norm": 1.6743440628051758,
+      "learning_rate": 4.408388003748829e-05,
+      "loss": 0.2866,
+      "step": 2020
+    },
+    {
+      "epoch": 0.9512652296157451,
+      "grad_norm": 1.5439425706863403,
+      "learning_rate": 4.4054592314901596e-05,
+      "loss": 0.286,
+      "step": 2030
+    },
+    {
+      "epoch": 0.9559512652296157,
+      "grad_norm": 1.317328691482544,
+      "learning_rate": 4.4025304592314905e-05,
+      "loss": 0.2674,
+      "step": 2040
+    },
+    {
+      "epoch": 0.9606373008434864,
+      "grad_norm": 1.3477058410644531,
+      "learning_rate": 4.399601686972821e-05,
+      "loss": 0.3005,
+      "step": 2050
+    },
+    {
+      "epoch": 0.9653233364573571,
+      "grad_norm": 1.8991141319274902,
+      "learning_rate": 4.396672914714152e-05,
+      "loss": 0.2924,
+      "step": 2060
+    },
+    {
+      "epoch": 0.9700093720712277,
+      "grad_norm": 1.406160593032837,
+      "learning_rate": 4.3937441424554824e-05,
+      "loss": 0.2977,
+      "step": 2070
+    },
+    {
+      "epoch": 0.9746954076850984,
+      "grad_norm": 1.7128149271011353,
+      "learning_rate": 4.390815370196814e-05,
+      "loss": 0.3003,
+      "step": 2080
+    },
+    {
+      "epoch": 0.979381443298969,
+      "grad_norm": 1.2714091539382935,
+      "learning_rate": 4.387886597938145e-05,
+      "loss": 0.2807,
+      "step": 2090
+    },
+    {
+      "epoch": 0.9840674789128397,
+      "grad_norm": 1.1022099256515503,
+      "learning_rate": 4.3849578256794756e-05,
+      "loss": 0.2889,
+      "step": 2100
+    },
+    {
+      "epoch": 0.9840674789128397,
+      "eval_loss": 0.04628630727529526,
+      "eval_pearson_cosine": 0.8264380630920911,
+      "eval_pearson_dot": 0.765122231613347,
+      "eval_pearson_euclidean": 0.8297712335935188,
+      "eval_pearson_manhattan": 0.8303968843751832,
+      "eval_runtime": 5.8458,
+      "eval_samples_per_second": 256.595,
+      "eval_spearman_cosine": 0.8280517554752953,
+      "eval_spearman_dot": 0.7620029087019149,
+      "eval_spearman_euclidean": 0.8362970969318975,
+      "eval_spearman_manhattan": 0.8368418361210694,
+      "eval_steps_per_second": 16.08,
+      "step": 2100
+    },
+    {
+      "epoch": 0.9887535145267105,
+      "grad_norm": 1.5780407190322876,
+      "learning_rate": 4.3820290534208064e-05,
+      "loss": 0.3019,
+      "step": 2110
+    },
+    {
+      "epoch": 0.993439550140581,
+      "grad_norm": 1.5804523229599,
+      "learning_rate": 4.3791002811621366e-05,
+      "loss": 0.254,
+      "step": 2120
+    },
+    {
+      "epoch": 0.9981255857544518,
+      "grad_norm": 1.5754133462905884,
+      "learning_rate": 4.3761715089034675e-05,
+      "loss": 0.2948,
+      "step": 2130
     }
   ],
   "logging_steps": 10,
@@ -1741,7 +1848,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }