Training in progress, step 1150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd192dd85ff6446dfa29041091b7f433f1d6a850202807fb731b90087b71d2ec
+oid sha256:19df8cfb4fb263762edd35195481b243b0e76f56e98ae181beceb2398a64b8c5
 size 29034840

last-checkpoint/global_step1150/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f621584d960c54af981bacd4e132f762eb9e48a25ebad8102f674e758ae624b
+size 43429616

last-checkpoint/global_step1150/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff47d6deb1356289fee8e2bc07a0056f08bc0bb2c57c6b654a85f3462cd42d3a
+size 43429616

last-checkpoint/global_step1150/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81e092ce23bea36d9f84e754f41af61de5207bbbe8eb34c3f2ae4274e56cec07
+size 43429616

last-checkpoint/global_step1150/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de1f8ac910500d5dec96234c0ad8b9087bc475a40ed3d32d641ac3f4625a5b4f
+size 43429616

last-checkpoint/global_step1150/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1d8f57ebe199b6160c4283125fd253980fc44b2d216970f98e39b9f2019c2bb
+size 637299

last-checkpoint/global_step1150/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a59940217878d056c0ec4cb1d8fbeda7666879dfdefc0e73fb244d7b2d08ee1
+size 637171

last-checkpoint/global_step1150/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:332e38fe883e969b04d02c7f8ee460470b9316344ea2066a08f8964ab917200d
+size 637171

last-checkpoint/global_step1150/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68dd6f1cba0b7e8d93d7b459f72081e50445095b21075bede743ce3b2d69d184
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step1100
+global_step1150

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d9fea52fb92cc51e76feeb2b139ce35723c0cb651da383e4f7eec2606ed6c2a
+oid sha256:274dc3860ee0c7f4d5348f60910a4b568498c04adfefb89f905b1c78a82c1312
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b5820ebfcc2e1cfe1ad2619a05ea9a484ff21635e13e386bf14abd302f2c0f7
+oid sha256:e9aa441491b9ca89e796944520fa1db332a67c0a1a920be83edd2d96d741716d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb8d96a68e732fca41980516622a50990bbd3ee989e72076a35c8608d9b4d136
+oid sha256:c1ee3434533b24fb771504fa8cceb5c2ea25fe0de1641128feaceccc65afe6ed
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce6f1db6d09f4d89a9b2bd8dc8eeb99f1fada2ec04376e23b5a7a13004994005
+oid sha256:93b4a44be1335173d2e3120bd0d1e6346f3e832d8935752c70ce1e98f017fa87
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d0c7456eafeee3179566bb381c9153771d7e0f21738d2398944d053915d0651
+oid sha256:7d461c8d7517d4b88333bff7984fc3bfc149292198b04bbc18a49aee698ffb5c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6174182295799255,
-  "best_model_checkpoint": "saves/CADICA_qwenvl_detect_classify_augmented/lora/sft/checkpoint-1100",
-  "epoch": 0.13475850663073108,
+  "best_metric": 0.6082175970077515,
+  "best_model_checkpoint": "saves/CADICA_qwenvl_detect_classify_augmented/lora/sft/checkpoint-1150",
+  "epoch": 0.14088389329576428,
   "eval_steps": 50,
-  "global_step": 1100,
+  "global_step": 1150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1965,11 +1965,100 @@
       "eval_steps_per_second": 0.779,
       "num_input_tokens_seen": 7552920,
       "step": 1100
+    },
+    {
+      "epoch": 0.1353710452972344,
+      "grad_norm": 1.6568269633234864,
+      "learning_rate": 8.07106356344834e-05,
+      "loss": 0.5067,
+      "num_input_tokens_seen": 7586336,
+      "step": 1105
+    },
+    {
+      "epoch": 0.13598358396373772,
+      "grad_norm": 9.881127130998916,
+      "learning_rate": 8.051838793910038e-05,
+      "loss": 0.5564,
+      "num_input_tokens_seen": 7620456,
+      "step": 1110
+    },
+    {
+      "epoch": 0.13659612263024104,
+      "grad_norm": 5.434757636785574,
+      "learning_rate": 8.032541847934146e-05,
+      "loss": 0.5854,
+      "num_input_tokens_seen": 7654064,
+      "step": 1115
+    },
+    {
+      "epoch": 0.13720866129674436,
+      "grad_norm": 8.431770854556952,
+      "learning_rate": 8.013173181896283e-05,
+      "loss": 0.5729,
+      "num_input_tokens_seen": 7687768,
+      "step": 1120
+    },
+    {
+      "epoch": 0.13782119996324768,
+      "grad_norm": 2.7261911659276343,
+      "learning_rate": 7.993733253868256e-05,
+      "loss": 0.6122,
+      "num_input_tokens_seen": 7721544,
+      "step": 1125
+    },
+    {
+      "epoch": 0.138433738629751,
+      "grad_norm": 2.456505697190831,
+      "learning_rate": 7.974222523607236e-05,
+      "loss": 0.5618,
+      "num_input_tokens_seen": 7755464,
+      "step": 1130
+    },
+    {
+      "epoch": 0.13904627729625432,
+      "grad_norm": 3.8454579857105626,
+      "learning_rate": 7.954641452544865e-05,
+      "loss": 0.5487,
+      "num_input_tokens_seen": 7789152,
+      "step": 1135
+    },
+    {
+      "epoch": 0.13965881596275764,
+      "grad_norm": 5.774785303618935,
+      "learning_rate": 7.934990503776363e-05,
+      "loss": 0.5132,
+      "num_input_tokens_seen": 7822128,
+      "step": 1140
+    },
+    {
+      "epoch": 0.14027135462926096,
+      "grad_norm": 6.086190598879861,
+      "learning_rate": 7.915270142049566e-05,
+      "loss": 0.5576,
+      "num_input_tokens_seen": 7855584,
+      "step": 1145
+    },
+    {
+      "epoch": 0.14088389329576428,
+      "grad_norm": 5.537023500299833,
+      "learning_rate": 7.89548083375394e-05,
+      "loss": 0.5403,
+      "num_input_tokens_seen": 7889016,
+      "step": 1150
+    },
+    {
+      "epoch": 0.14088389329576428,
+      "eval_loss": 0.6082175970077515,
+      "eval_runtime": 19.2261,
+      "eval_samples_per_second": 3.121,
+      "eval_steps_per_second": 0.78,
+      "num_input_tokens_seen": 7889016,
+      "step": 1150
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 7552920,
+  "num_input_tokens_seen": 7889016,
   "num_train_epochs": 1,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -1984,7 +2073,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 475129840533504.0,
+  "total_flos": 496216376475648.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null